CN107277128A - The method and device of request processing order-preserving in a kind of distributed storage agreement - Google Patents
The method and device of request processing order-preserving in a kind of distributed storage agreement Download PDFInfo
- Publication number
- CN107277128A CN107277128A CN201710452743.6A CN201710452743A CN107277128A CN 107277128 A CN107277128 A CN 107277128A CN 201710452743 A CN201710452743 A CN 201710452743A CN 107277128 A CN107277128 A CN 107277128A
- Authority
- CN
- China
- Prior art keywords
- request
- write request
- queue
- inode
- write
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 title claims abstract description 28
- 238000003860 storage Methods 0.000 title claims abstract description 28
- 230000007246 mechanism Effects 0.000 claims abstract description 18
- 230000002618 waking effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 description 9
- 230000008275 binding mechanism Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005059 dormancy Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007717 exclusion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method and device of request processing order-preserving in distributed storage agreement, this method includes:In the sets of threads module of NFS protocol, correspondence one request queue of configuration of each thread is given, single inode nodes are deposited in request queue;Write request is received using far call agreement RPC, the inode information in write request is parsed;Write request is added in the inode nodes of corresponding request queue according to preset algorithm;The corresponding thread of write request is waken up, makes thread according to balanced polling mechanism, the write request in each inode nodes in circular treatment request queue.This method, which is realized, avoids the empty risk of file, improves security.
Description
Technical field
Request is handled in technical field of distributed memory of the present invention, more particularly to a kind of distributed storage agreement
The method and device of order-preserving.
Background technology
At present, in distributed NAS storages, two large divisions, NAS protocol servers and storage system are generally divided into;NAS is assisted
View service end is most commonly used that NFS protocol, and NFS service ends are responsible for interacting there is provided file service to client with NFS clients.When
When NFS clients write data, based on caching mechanism, the dirty data after caching can be continuously transmitted in sequence at NFS service ends
Reason;NFS service ends are multi-thread mechanisms, and multiple threads handle request simultaneously, and lower floor's storage system is given different write requests
Processing;So under mechanism, when client writes single file, write request is continuously transmitted in sequence to service end, but service end meeting
Multi-thread concurrent handles these and asked, and one, not order-preserving can be caused, file has the risk for cavity occur, and security is relatively low;Two,
Due to identical file concurrent processing, resource exclusive reference is had, performance shake is big, in the case of matchmaker's money constant code stream of scene, meeting
There is frame losing risk.
The content of the invention
It is an object of the invention to provide a kind of method and device of request processing order-preserving in distributed storage agreement, to realize
The empty risk of file is avoided, security is improved.
In order to solve the above technical problems, the method that the present invention provides request processing order-preserving in a kind of distributed storage agreement,
This method includes:
In the sets of threads module of NFS protocol, correspondence one request queue of configuration of each thread is given, is deposited in request queue
Put single inode nodes;
Write request is received using far call agreement RPC, the inode information in write request is parsed;
Write request is added in the inode nodes of corresponding request queue according to preset algorithm;
The corresponding thread of write request is waken up, makes thread according to balanced polling mechanism, it is each in circular treatment request queue
Write request in inode nodes.
It is preferred that, the preset algorithm includes hash algorithm or polling algorithm.
It is preferred that, after the inode information parsed in write request, in addition to:
Parsing write request, which is obtained, writes offset information.
It is preferred that, described that write request is added in the inode nodes of corresponding request queue according to preset algorithm, bag
Include:
If existing identical write request in request queue, according to write offset information the write request received is put into it is same
In the request chained list correspondence position of individual inode nodes;
If not having identical write request in request queue, write request is directly placed into request queue tail end.
The present invention also provides a kind of device of request processing order-preserving in distributed storage agreement, for realizing the above method,
Including:
Configuration module, in the sets of threads module of NFS protocol, giving correspondence one request queue of configuration of each thread,
Single inode nodes are deposited in request queue;
Parsing module, for receiving write request using far call agreement RPC, parses the inode information in write request;
Add module, for write request to be added in the inode nodes of corresponding request queue according to preset algorithm;
Loop module, for waking up the corresponding thread of write request, makes thread according to balanced polling mechanism, circular treatment request
The write request in each inode nodes in queue.
It is preferred that, the preset algorithm includes hash algorithm or polling algorithm.
It is preferred that, the parsing module is additionally operable to parsing write request acquisition and writes offset information.
It is preferred that, if if the add module is specifically for existing identical write request in request queue, it is inclined according to writing
Move information the write request received is put into the request chained list correspondence position of same inode nodes;If not having in request queue
There is identical write request, write request is directly placed into request queue tail end.
The method and device of request processing order-preserving in a kind of distributed storage agreement provided by the present invention, in NFS protocol
Sets of threads module in, give correspondence one request queue of configuration of each thread, single inode sections deposited in request queue
Point;Write request is received using far call agreement RPC, the inode information in write request is parsed;To be write according to preset algorithm please
Ask and be added in the inode nodes of corresponding request queue;The corresponding thread of write request is waken up, makes thread according to balanced poll machine
System, the write request in each inode nodes in circular treatment request queue.It can be seen that, using file and thread binding mechanism,
The write request of identical file is corresponded on the write request queue of same thread, during thread process request queue, using poll side
Different files in formula equilibrium treatment request queue, so solve the problems, such as write request order-preserving in monofile, prevent document order
Occur cavity when writing, improve security.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is the flow chart of the method for request processing order-preserving in a kind of distributed storage agreement provided by the present invention;
Fig. 2 is write request protection processing schematic diagram in NFS protocol;
Fig. 3 is the structural representation of the device of request processing order-preserving in a kind of distributed storage agreement provided by the present invention
Figure.
Embodiment
The core of the present invention is to provide a kind of method and device of request processing order-preserving in distributed storage agreement, to realize
The empty risk of file is avoided, security is improved.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
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.
Term is explained as follows:
NFSNetwork File System are NFS;
NAS Network Attach Storage are network attached storage, are the Storage Service Types of Ethernet.
Fig. 1 is refer to, Fig. 1 is the method for request processing order-preserving in a kind of distributed storage agreement provided by the present invention
Flow chart, this method includes:
S11:In the sets of threads module of NFS protocol, correspondence one request queue of configuration of each thread is given, in request queue
The single inode nodes of middle storage;
S12:Write request is received using far call agreement RPC, the inode information in write request is parsed;
S13:Write request is added in the inode nodes of corresponding request queue according to preset algorithm;
S14:The corresponding thread of write request is waken up, makes thread according to balanced polling mechanism, in circular treatment request queue
Write request in each inode nodes.
It can be seen that, using file and thread binding mechanism, the write request of identical file is corresponded to writing for same thread please
Ask in queue, during thread process request queue, using the different files in polling mode equilibrium treatment request queue, so solve
Write request order-preserving problem in monofile, prevents occurring cavity when document order from writing, and improves security.
Wherein, inode nodes are exactly an inode number, are globally unique, inode number one texts of unique correspondence
Part.The write request for belonging to same file is hung under this inode number, handled using single thread, the place of request is ensured that
Make sequence in order.
Based on the above method, specifically, the preset algorithm includes hash algorithm or polling algorithm.
Further, in step S12, after the inode information parsed in write request, in addition to:Parsing is write please
Acquisition is asked to write offset information.
Further, step S13 process is specially:It is inclined according to writing if existing identical write request in request queue
Move information the write request received is put into the request chained list correspondence position of same inode nodes;If not having in request queue
There is identical write request, write request is directly placed into request queue tail end.
This method corresponds to the write request of identical file in the queue of single thread, and is arranged according to skew order, line
When journey handles request queue, using the different files in polling mode equilibrium treatment request queue, so solve in monofile
Order-preserving problem, prevents occurring cavity when document order from writing, and avoids the resource contention of multiple threads identical file appearance, subtracts
The factor of performance shake is lacked.Also, equilibrium treatment mechanism of the write request of different files in same thread, is effectively improved
The writing speed of overall business, makes performance more stable, it is ensured that the height of business under the constant code stream scene of low time delay requirement
Performance.
Based on this method, specific implementation process is as follows:
First, in the sets of threads module of NFS protocol, one request queue of correspondence of each thread is given, queue storage is single
Inode nodes, same inode multiple request internal correlations composition queue;
Then, RPC is received after write request, the inode information in analysis request, and corresponding to one according to regulation algorithm please
Ask in queue, if having there is this inode request in request queue, be ranked up according to skew in request and be inserted into inode
The correspondence position of request group;
Finally, wake up correspondence thread to be handled, thread is each in circular treatment queue according to balanced polling mechanism
Write request in inode, calls lower floor's storage system interface, writes data in storage, after the completion of record result asking back
Asynchronous transmission response queue should be put into, if each inode request handles completion in queue, into dormancy, wait is called out
Wake up.
Detailed, the treatment mechanism that this method is bound using file with thread is main to include following several steps:
(1) global two-dimentional queue is created, queue number is corresponded with business processing Thread Count;
(2) write request algorithm corresponding with queue is realized;
Wherein, using two kinds of algorithms of hash or poll, for the different scene of traffic pressure;
(3) RPC receives request processing, and analysis request key message obtains inode and writes offset information;
(4) algorithm is called, corresponding queue index is calculated;
(5) whether in this queue had this inode write request, if not provided, being directly placed into rear of queue if checking;
(6) if there are inode write requests in queue, sorted according to skew, be put into same inode request chained list correspondence
In position so that the write request of same file is arranged by skew order;
(7) thread process is waken up;
(8) thread loops queue obtains request, according to polling mechanism, the request chained list in processing queue on each inode,
Specifically obtained according to skew order;
Wherein, each inode handles a write request, the then next inode processing of poll;
(9) obtain request after start to process, call storage system interface carry out data write-in, after the completion of record result please
Response is asked to be put into asynchronous transmission response queue;
(10) the 8th, 9 steps are repeated, until the processing of this queue request is completed, thread enters dormancy, waits and waking up.With reference to figure
2, Fig. 2 be write request protection processing schematic diagram in NFS protocol.
This method binds the mechanism of thread process using identical file, enables high speed serialization processing of the request without mutual exclusion;
So as to improve the stability of monofile, the high request of constant code stream scene low time delay is met;Simultaneously because being gone here and there according to skew
Row execution please handle, it is to avoid the empty risk of file for being sequentially written in file and causing extremely during concurrent processing, improve reliable
Property, uniformity;And each request equilibrium treatment of the file in same thread, the writing speed of file is effectively improved,
Make performance more stable.
This method designs request queue mapping mechanism and obtains the equilibrating mechanism of request processing so that in single file
Write request can the high speed serialization without mutual exclusion handle, and equilibrium treatment between different file;Reach order-preserving perform target with
And the effect of improving performance stability.Simultaneously present invention can apply in other operation flows, such as the processing of read request, one
Sample, which can be reached, improves the stable effect of performance.
Fig. 3 is refer to, Fig. 3 is the device of request processing order-preserving in a kind of distributed storage agreement provided by the present invention
Structural representation, the device is used to realize the above method, and the device includes:
Configuration module 101, in the sets of threads module of NFS protocol, giving the configuration of each thread correspondence one request team
Row, deposit single inode nodes in request queue;
Parsing module 102, for receiving write request using far call agreement RPC, parses the inode letters in write request
Breath;
Add module 103, the inode nodes for write request to be added to corresponding request queue according to preset algorithm
In;
Loop module 104, for waking up the corresponding thread of write request, makes thread according to balanced polling mechanism, circular treatment
The write request in each inode nodes in request queue.
It can be seen that, using file and thread binding mechanism, the write request of identical file is corresponded to writing for same thread please
Ask in queue, during thread process request queue, using the different files in polling mode equilibrium treatment request queue, so solve
Write request order-preserving problem in monofile, prevents occurring cavity when document order from writing, and improves security.
Based on said apparatus, specifically, preset algorithm includes hash algorithm or polling algorithm.
Further, parsing module is additionally operable to parsing write request acquisition and writes offset information.
Further, if if add module is specifically for existing identical write request in request queue, according to writing skew
The write request received is put into the request chained list correspondence position of same inode nodes by information;If not having in request queue
Identical write request, request queue tail end is directly placed into by write request.
The present invention binds treatment mechanism using file and thread, and balanced sequential processes request can reduce file performance and tremble
It is dynamic, improve the performance of constant code stream scene.The present invention is by using file and thread binding mechanism, to solve the problems, such as order-preserving, prevents
There is cavity when only document order is write;And single thread processing identical file, reduce the factor of performance shake, it is ensured that low
Under the constant code stream scene of delay requirement, the high-performance of business embodies.
The embodiment of each in this specification is described by the way of progressive, what each embodiment was stressed be with it is other
Between the difference of embodiment, each embodiment same or similar part mutually referring to.For being filled disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part
Explanation.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, generally describes the composition and step of each example according to function in the above description.These
Function is performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.Specialty
Technical staff can realize described function to each specific application using distinct methods, but this realization should not
Think beyond the scope of this invention.
Directly it can be held with reference to the step of the method or algorithm that the embodiments described herein is described with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The method and device that request in a kind of distributed storage agreement provided by the present invention handles order-preserving is carried out above
It is discussed in detail.Specific case used herein is set forth to the principle and embodiment of the present invention, above example
Explanation be only intended to help to understand the method and its core concept of the present invention.It should be pointed out that for the common of the art
For technical staff, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these
Improve and modification is also fallen into the protection domain of the claims in the present invention.
Claims (8)
1. a kind of method of request processing order-preserving in distributed storage agreement, it is characterised in that including:
In the sets of threads module of NFS protocol, correspondence one request queue of configuration of each thread is given, deposits single in request queue
Individual inode nodes;
Write request is received using far call agreement RPC, the inode information in write request is parsed;
Write request is added in the inode nodes of corresponding request queue according to preset algorithm;
The corresponding thread of write request is waken up, makes thread according to balanced polling mechanism, each inode in circular treatment request queue
Write request in node.
2. the method as described in claim 1, it is characterised in that the preset algorithm includes hash algorithm or polling algorithm.
3. the method as described in claim 1, it is characterised in that after the inode information parsed in write request, also wrap
Include:
Parsing write request, which is obtained, writes offset information.
4. method as claimed in claim 3, it is characterised in that described that write request is added to corresponding ask according to preset algorithm
In the inode nodes for asking queue, including:
If existing identical write request in request queue, according to write offset information the write request received is put into it is same
In the request chained list correspondence position of inode nodes;
If not having identical write request in request queue, write request is directly placed into request queue tail end.
5. the device of request processing order-preserving in a kind of distributed storage agreement, it is characterised in that for realizing Claims 1-4
Method described in middle any one, including:
Configuration module, in the sets of threads module of NFS protocol, giving correspondence one request queue of configuration of each thread, is being asked
Seek the inode nodes that queue for storing is single;
Parsing module, for receiving write request using far call agreement RPC, parses the inode information in write request;
Add module, for write request to be added in the inode nodes of corresponding request queue according to preset algorithm;
Loop module, for waking up the corresponding thread of write request, makes thread according to balanced polling mechanism, circular treatment request queue
In each inode nodes in write request.
6. device as claimed in claim 5, it is characterised in that the preset algorithm includes hash algorithm or polling algorithm.
7. device as claimed in claim 5, it is characterised in that the parsing module is additionally operable to parsing write request acquisition and writes skew
Information.
8. device as claimed in claim 7, it is characterised in that if if the add module in request queue specifically for having deposited
In identical write request, according to the request chained list pair for writing offset information and be put into the write request received same inode nodes
Answer in position;If not having identical write request in request queue, write request is directly placed into request queue tail end.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710452743.6A CN107277128B (en) | 2017-06-15 | 2017-06-15 | Method and device for requesting processing order preservation in distributed storage protocol |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710452743.6A CN107277128B (en) | 2017-06-15 | 2017-06-15 | Method and device for requesting processing order preservation in distributed storage protocol |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107277128A true CN107277128A (en) | 2017-10-20 |
CN107277128B CN107277128B (en) | 2020-09-22 |
Family
ID=60067248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710452743.6A Active CN107277128B (en) | 2017-06-15 | 2017-06-15 | Method and device for requesting processing order preservation in distributed storage protocol |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107277128B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108762930A (en) * | 2018-05-30 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of optimization method, system and the associated component of User space NFS threads |
CN109801425A (en) * | 2018-12-27 | 2019-05-24 | 平安科技(深圳)有限公司 | Queue poll reminding method, device, equipment and storage medium in the label business of face |
CN110377270A (en) * | 2019-06-25 | 2019-10-25 | 苏州浪潮智能科技有限公司 | A kind of method and system for realizing multi stream function |
CN111209263A (en) * | 2020-01-14 | 2020-05-29 | 中国建设银行股份有限公司 | Data storage method, device, equipment and storage medium |
CN111241036A (en) * | 2020-01-21 | 2020-06-05 | 苏州浪潮智能科技有限公司 | Asynchronous IO data processing method, device, equipment and medium |
CN113033789A (en) * | 2019-12-24 | 2021-06-25 | 中科寒武纪科技股份有限公司 | Bus system for order preservation, integrated circuit device, board card and order preservation method |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727299A (en) * | 2010-02-08 | 2010-06-09 | 北京同有飞骥科技有限公司 | RAID5-orientated optimal design method for writing operation in continuous data storage |
CN102622350A (en) * | 2011-01-26 | 2012-08-01 | 腾讯科技(深圳)有限公司 | Method, device and system for writing data |
CN103810072A (en) * | 2012-11-09 | 2014-05-21 | 上海飞田通信技术有限公司 | Device and method for guaranteeing order execution of multithread tasks |
CN105159774A (en) * | 2015-07-08 | 2015-12-16 | 清华大学 | API request order-preserving processing method and system |
CN105262680A (en) * | 2015-10-21 | 2016-01-20 | 浪潮(北京)电子信息产业有限公司 | Multi-threaded NAS Gateway applied to cloud storage system |
CN105353987A (en) * | 2015-11-13 | 2016-02-24 | 曙光信息产业股份有限公司 | File processing method and device |
CN105700824A (en) * | 2015-12-29 | 2016-06-22 | 浪潮(北京)电子信息产业有限公司 | Read operation request processing method and system of mechanical hard disk of storage system |
CN106209684A (en) * | 2016-07-14 | 2016-12-07 | 深圳市永达电子信息股份有限公司 | A kind of method forwarding detection scheduling based on Time Triggered |
US20170123848A1 (en) * | 2015-10-30 | 2017-05-04 | International Business Machines Corporation | Multi-task processing in a distributed storage network |
CN106648905A (en) * | 2017-01-12 | 2017-05-10 | 南京南瑞集团公司 | Electric power big data distributed control system and building method thereof |
-
2017
- 2017-06-15 CN CN201710452743.6A patent/CN107277128B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727299A (en) * | 2010-02-08 | 2010-06-09 | 北京同有飞骥科技有限公司 | RAID5-orientated optimal design method for writing operation in continuous data storage |
CN102622350A (en) * | 2011-01-26 | 2012-08-01 | 腾讯科技(深圳)有限公司 | Method, device and system for writing data |
CN103810072A (en) * | 2012-11-09 | 2014-05-21 | 上海飞田通信技术有限公司 | Device and method for guaranteeing order execution of multithread tasks |
CN105159774A (en) * | 2015-07-08 | 2015-12-16 | 清华大学 | API request order-preserving processing method and system |
CN105262680A (en) * | 2015-10-21 | 2016-01-20 | 浪潮(北京)电子信息产业有限公司 | Multi-threaded NAS Gateway applied to cloud storage system |
US20170123848A1 (en) * | 2015-10-30 | 2017-05-04 | International Business Machines Corporation | Multi-task processing in a distributed storage network |
CN105353987A (en) * | 2015-11-13 | 2016-02-24 | 曙光信息产业股份有限公司 | File processing method and device |
CN105700824A (en) * | 2015-12-29 | 2016-06-22 | 浪潮(北京)电子信息产业有限公司 | Read operation request processing method and system of mechanical hard disk of storage system |
CN106209684A (en) * | 2016-07-14 | 2016-12-07 | 深圳市永达电子信息股份有限公司 | A kind of method forwarding detection scheduling based on Time Triggered |
CN106648905A (en) * | 2017-01-12 | 2017-05-10 | 南京南瑞集团公司 | Electric power big data distributed control system and building method thereof |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108762930A (en) * | 2018-05-30 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of optimization method, system and the associated component of User space NFS threads |
CN109801425A (en) * | 2018-12-27 | 2019-05-24 | 平安科技(深圳)有限公司 | Queue poll reminding method, device, equipment and storage medium in the label business of face |
CN110377270A (en) * | 2019-06-25 | 2019-10-25 | 苏州浪潮智能科技有限公司 | A kind of method and system for realizing multi stream function |
CN110377270B (en) * | 2019-06-25 | 2023-01-06 | 苏州浪潮智能科技有限公司 | Method and system for realizing multi stream function |
CN113033789A (en) * | 2019-12-24 | 2021-06-25 | 中科寒武纪科技股份有限公司 | Bus system for order preservation, integrated circuit device, board card and order preservation method |
CN113033789B (en) * | 2019-12-24 | 2024-03-26 | 中科寒武纪科技股份有限公司 | Bus system, integrated circuit device, board card and order preserving method for order preserving |
CN111209263A (en) * | 2020-01-14 | 2020-05-29 | 中国建设银行股份有限公司 | Data storage method, device, equipment and storage medium |
CN111241036A (en) * | 2020-01-21 | 2020-06-05 | 苏州浪潮智能科技有限公司 | Asynchronous IO data processing method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107277128B (en) | 2020-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107277128A (en) | The method and device of request processing order-preserving in a kind of distributed storage agreement | |
Wang et al. | HydraDB: a resilient RDMA-driven key-value middleware for in-memory cluster computing | |
EP2590087B1 (en) | Database log parallelization | |
US9218405B2 (en) | Batch processing and data synchronization in cloud-based systems | |
CN101277272B (en) | Method for implementing magnanimity broadcast data warehouse-in | |
EP3785139A1 (en) | System and method for heterogeneous database replication from a remote server | |
CN105471989B (en) | A kind of date storage method | |
CN108170768A (en) | database synchronization method, device and readable medium | |
CN112084258A (en) | Data synchronization method and device | |
US9984139B1 (en) | Publish session framework for datastore operation records | |
Adya et al. | Fast key-value stores: An idea whose time has come and gone | |
US20200042475A1 (en) | Elastic method of remote direct memory access memory advertisement | |
WO2020263370A1 (en) | Parallel processing of filtered transaction logs | |
CN109240617A (en) | Distributed memory system write request processing method, device, equipment and storage medium | |
US20220358106A1 (en) | Proxy-based database scaling | |
CN108196787A (en) | The quota management method and cluster storage system of cluster storage system | |
CN104079600B (en) | File memory method, device, access client and meta data server system | |
CN104899161A (en) | Cache method based on continuous data protection of cloud storage environment | |
CN108965054A (en) | A kind of client and service end data rapid interactive method | |
CN108733701A (en) | A kind of query page buffer control method applied to online education | |
CN109271367A (en) | Distributed file system multinode snapshot rollback method and system | |
CN108984779A (en) | Distributed file system snapshot rollback metadata processing method, device and equipment | |
CN109254958A (en) | Distributed data reading/writing method, equipment and system | |
CN108769244B (en) | Storage task information acquisition method and related device | |
CN104850548B (en) | A kind of method and system for realizing big data platform input/output processing |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200826 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Applicant after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 450018 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Applicant before: ZHENGZHOU YUNHAI INFORMATION TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |