CN104731533B - Method for writing data and device - Google Patents
Method for writing data and device Download PDFInfo
- Publication number
- CN104731533B CN104731533B CN201510146467.1A CN201510146467A CN104731533B CN 104731533 B CN104731533 B CN 104731533B CN 201510146467 A CN201510146467 A CN 201510146467A CN 104731533 B CN104731533 B CN 104731533B
- Authority
- CN
- China
- Prior art keywords
- caching
- write operation
- write
- operation requests
- module
- 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.)
- Active
Links
Abstract
The present invention proposes that a kind of method for writing data and device, the method for writing data include：Receive the write operation requests that application is sent；By the first caching of write operation requests deposit；When the type of the write operation requests is returned or write and during simultaneously operating or when the described first caching has met caching switching condition to write immediately, the caching for preserving the write operation requests received is switched to the second caching by the described first caching；Write operation is performed to the write operation requests in the described first caching.The present invention can give full play to batch read-write and the concurrency of writing disk manipulation, can improve handling capacity to maximum performance on the premise of not influencing using write operation semanteme.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of method for writing data and device.
Background technology
In the storage system handled up in height, the pressure of read-write is often per second to reach a request amounts up to ten thousand, and the number asked
It differs in size according to amount.Particularly in the storage engines of structuring, often write request is intended merely to change or update effective
Several short attribute fields, and require to read immediately as it can be seen that ensure conversation affair after updating.
Meanwhile more and more systems use system design (the Write Append Logging based on daily record；Following letter
Claim：WAL) design, all writing is become into sequential write as far as possible, to reduce the movement of magnetic head and perdurable data.Since WAL is set
Meter is needed in real time by data rule, this needs synchronization (sync) interface of call operation system, it will has substantial amounts of small data please
Needs is asked to perform rule in real time.
However, the reason of the machinery scheduling due to disk read-write magnetic head, it is often necessary to which being dispatched to different magnetic tracks can just open
Beginning is written and read.In current Serial Advanced Technology Attachment (Serial Advanced Technology Attachment；With
Lower abbreviation：SATA) under disk ring border, since the least unit write every time is a sector, if data volume is too small, in sector
Extra space will be wasted.And in driving layer or operating system layer, usual write buffer for a page-size (4K or
Person 8K), therefore if calling a writing disk manipulation for each update or write-in of small data quantity, delay can be increased, hardly possible
To improve handling capacity.
The content of the invention
The purpose of the present invention is intended to solve at least some of the technical problems in related technologies.
For this purpose, first purpose of the present invention is to propose a kind of method for writing data.This method, which can give full play to, to be criticized
Amount read-write and the concurrency of writing disk manipulation, can improve to maximum performance on the premise of not influencing using write operation semanteme and handle up
Amount.
Second object of the present invention is to propose a kind of data transfer apparatus.
To achieve these goals, the method for writing data of first aspect present invention embodiment, including：Application is received to send
Write operation requests；By the first caching of write operation requests deposit；When the type of the write operation requests returns immediately to write
Or write and during simultaneously operating or when the described first caching has met caching switching condition, will preserve the write operation that receives please
The caching asked is switched to the second caching by the described first caching；Write-in behaviour is performed to the write operation requests in the described first caching
Make.
The method for writing data of the embodiment of the present invention after receiving the write operation requests that application is sent, will first receive
The first caching of write operation requests deposit, when above-mentioned write operation requests type for write return or write immediately and during simultaneously operating or
Person is cut when the above-mentioned first caching has met caching switching condition, by the caching for preserving the write operation requests received by the first caching
The second caching is changed to, then write operation is performed to the write operation requests in the above-mentioned first caching, so as to give full play to batch
Read-write and the concurrency of writing disk manipulation, and then can improve to maximum performance and gulp down on the premise of not influencing using write operation semanteme
The amount of spitting.
To achieve these goals, the data transfer apparatus of second aspect of the present invention embodiment, including：Receiving module is used
In the write operation requests for receiving application transmission；Module is stored in, for the write operation requests deposit for receiving the receiving module
One caching；Handover module, for when the type of the write operation requests is returned or write to write immediately and during simultaneously operating or is worked as
When first caching has met caching switching condition, the caching for preserving the write operation requests received is cut by the described first caching
It is changed to the second caching；Writing module, for performing write operation to the write operation requests in the described first caching.
The data transfer apparatus of the embodiment of the present invention, after receiving module receives the write operation requests that application is sent, deposit
Module first caches the write operation requests received deposit first, when the type of above-mentioned write operation requests is returned or write to write immediately
And during simultaneously operating or when the above-mentioned first caching has met caching switching condition, handover module writes behaviour by what preservation received
Make the caching asked and the second caching is switched to by the first caching, then by writing module to the write operation requests in the above-mentioned first caching
Write operation is performed, so as to give full play to batch read-write and the concurrency of writing disk manipulation, and then can not influence to apply
Maximum performance handling capacity is improved on the premise of write operation semanteme.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
It obtains substantially or is recognized by the practice of the present invention.
Description of the drawings
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of method for writing data one embodiment of the present invention；
Fig. 2 is the schematic diagram of another embodiment of method for writing data of the present invention；
Fig. 3 is the structure diagram of data transfer apparatus one embodiment of the present invention；
Fig. 4 is the structure diagram of another embodiment of data transfer apparatus of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or has the function of same or like element.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not considered as limiting the invention.On the contrary, this
The embodiment of invention includes falling into all changes in the range of the spirit and intension of attached claims, modification and equivalent
Object.
The caching mechanism that method for writing data provided by the invention is switched each other based on two, realizes sync on this basis
(data brush) and the parallel execution of write operation are operated, the promotion handled up so as to fulfill write-in.
Semantic according to the calling of application, write operation requests can be divided into following 3 type：It writes and returns, write not immediately immediately
It returns and writes and three kinds of simultaneously operating.Specifically, (1) is write returns immediately：What is focused on is low delay, do not require immediately sync to magnetic
Disk, but data can not lose.(2) write and do not return immediately：What is focused on is to handle up, and is chiefly used in high concurrent write operation, does not require generally
Sync is to disk immediately, but data also require persistently lose.(3) write and sync：What is focused on is persistence, is chiefly used in key
The write operation (such as metadata) of data, it is desirable that the data of write-in immediately brush to prevent power down from losing.
In practical applications, the write operation requests of this 3 type can mix intersection and reach, wherein (2) type is in the majority, secondly
It is (1) type, (3) type is fewer.Method for writing data provided by the invention is used for the write operation requests of this 3 type
Processing mode it is as follows：
(1) write and return immediately：Once receiving such write operation requests, caching switching can be triggered, under switching
Write operation requests in the caching come perform write operation.Judge whether to meet synchronous (sync) operation trigger condition simultaneously, such as
Fruit is then to perform sync semanteme brushs, will perform the data that write operation write and is stored in disk, if being at this moment unsatisfactory for sync
Trigger condition is operated, then returns, continues to write operation requests.
(2) write and do not return immediately：For such write operation requests, caching is directly stored in, it is slow when checking
When depositing switching condition and being satisfied, triggering caching exchanges, to the write operation requests execution write operation in the caching that switch, but
Sync operations are not carried out.
(3) write and sync is operated：Such write operation requests once reach, no matter current cache whether have request or
How many request of person, triggering caching, which switches, immediately simultaneously performing sync semanteme brushs, will perform the data that write operation write and deposits
Enter disk.
Fig. 1 is the flow chart of method for writing data one embodiment of the present invention, as shown in Figure 1, the method for writing data can
To include：
Step 101, the write operation requests that application is sent are received.
Step 102, by the first caching of above-mentioned write operation requests deposit.
Step 103, when above-mentioned write operation requests type for write return or write immediately and during synchronous (sync) operation or
When the above-mentioned first caching has met caching switching condition, the caching for preserving the write operation requests received is switched by the first caching
For the second caching.
Specifically, the type of above-mentioned write operation requests can be determined according to the mark carried in write operation requests, such as：When
When sync marks are carried in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests is writes and simultaneously operating；When
When return mark immediately is write in carrying in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests is returned immediately to write
It returns；When not return mark immediately is write in carrying in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests is to write
It does not return immediately.
Wherein, the first caching, which has met caching switching condition, to be：The write operation requests cached in above-mentioned first caching
Item number reach first threshold and/or, it is above-mentioned first caching caching period have timed out.Wherein, the size of first threshold can be with
In specific implementation, according to the sets itselfs such as demand and/or system performance are realized, the present embodiment does not make the size of first threshold
It limits, for example, above-mentioned first threshold can be 10.The caching period of above-mentioned first caching can equally implement
When, according to the sets itselfs such as demand and/or system performance are realized, the present embodiment is to the length of the caching period of the above-mentioned first caching
It is not construed as limiting, for example, the caching period of above-mentioned first caching can be 5 seconds.
Step 104, write operation is performed to the write operation requests in the first caching.
Further, in the present embodiment, when the type of above-mentioned write operation requests to write and sync operations or met same
During step operation trigger condition, the data that write operation write will be performed and be stored in disk.That is, when the write operation received
The type of request for write and sync operate when or when met sync operate trigger condition when, can not only trigger step 103~
The execution of step 104 also triggers and performs sync semanteme brushs, will perform the data that write operation write and is stored in disk.
Wherein, having met sync operations trigger condition can be：The data entry that write operation is write is performed to have reached
The caching period of second threshold and/or above-mentioned first caching has timed out.
Wherein, the size of second threshold can voluntarily be set in specific implementation according to realization demand and/or system performance etc.
Fixed, the present embodiment is not construed as limiting the size of second threshold, for example, above-mentioned second threshold can be 30.In the present embodiment,
After carrying out caching switching, the write operation requests in being cached to first switched perform write operation, simply delay first
It deposits the data entry entrained by the write operation requests of preservation and writes another level cache, such as：The write operation that buffer is preserved please
Entrained data entry is asked to write cache, the data entry entrained by above-mentioned write operation requests is not write into disk.It is holding
The data entry that row write operation is write has reached second threshold and/or the caching period of the first caching has timed out (this meaning
Current cache, through a long time does not write data) in the case of, it can just trigger and perform sync semanteme brushs, execution is write
Enter the write data deposit disk of operation.
In addition, as previously mentioned, when the write operation requests received type for write and sync operate when, no matter first caching
In whether have request or how many request, can trigger immediately caching switch and perform sync semanteme brushs, write-in will be performed
The write data deposit disk of operation.
Further, in the present embodiment, after step 104, write operation response can also be returned to above application, with upward
State the completion status of the above-mentioned write operation of applicative notifications.That is, the present embodiment to switch first caching in write
Operation requests perform batch write operation, and the return of write request is just called after being finished, and write operation response is returned to above application,
With to the completion status of the above-mentioned write operation of above-mentioned applicative notifications.
Above-mentioned method for writing data is received using the write operation requests that after the write operation requests sent, will first receive
The first caching of deposit, when the type of above-mentioned write operation requests is returned or write and during simultaneously operating or when above-mentioned the to write immediately
When one caching has met caching switching condition, the caching for preserving the write operation requests received is switched to second by the first caching and is delayed
It deposits, then write operation is performed to the write operation requests in the above-mentioned first caching, so as to give full play to batch read-write with writing disk
The concurrency of operation, and then can improve handling capacity to maximum performance on the premise of not influencing using write operation semanteme.
Fig. 2 is the schematic diagram of another embodiment of method for writing data of the present invention, as shown in Fig. 2, behaviour is write in application transmission
Make all to be put into the first caching when request reaches but do not return immediately, return or write immediately to write when having received type and
During the write operation requests of sync operations or when the above-mentioned first caching has met caching switching condition, writing for reception will be preserved
The caching of operation requests is switched to the second caching by the first caching.In the embodiment of the present invention, caching handoff procedure is a pointer
Exchange process, lock cost is small, and the second caching after switching can continue to write operation requests, by input and output (Input
Output；Hereinafter referred to as：IO) module performs write operation to the write operation requests being switched in the get off first caching, and holds
Row sync, specific flow refer to the description in embodiment illustrated in fig. 1 of the present invention, and details are not described herein.Meeting after being finished
The return of write request is just called, write operation response is returned to application, with to the completion shape of the above-mentioned write operation of above-mentioned applicative notifications
State.
Fig. 3 is the structure diagram of data transfer apparatus one embodiment of the present invention, and the data write-in in the present embodiment fills
The flow of embodiment illustrated in fig. 1 of the present invention can be realized by putting, as shown in figure 3, the data transfer apparatus can include：Receiving module
31st, module 32, handover module 33 and writing module 34 are stored in；
Wherein, receiving module 31, for receiving the write operation requests that application is sent.
Module 32 is stored in, for the first caching of write operation requests deposit for receiving receiving module 31.
Handover module 33, for when the type of above-mentioned write operation requests for write return or write immediately and sync operate when or
Person is cut when the above-mentioned first caching has met caching switching condition, by the caching for preserving the write operation requests received by the first caching
It is changed to the second caching；Specifically, the type of above-mentioned write operation requests can be determined according to the mark carried in write operation requests, example
Such as：When carrying sync marks in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests is to write and synchronously grasp
Make；When return mark immediately is write in carrying in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests is vertical to write
Return；When not return mark immediately is write in carrying in above-mentioned write operation requests, it may be determined that the type of above-mentioned write operation requests
It is not returned immediately to write.
Wherein, the first caching, which has met caching switching condition, to be：The write operation requests cached in above-mentioned first caching
Item number reach first threshold and/or, it is above-mentioned first caching caching period have timed out.Wherein, the size of first threshold can be with
In specific implementation, according to the sets itselfs such as demand and/or system performance are realized, the present embodiment does not make the size of first threshold
It limits, for example, above-mentioned first threshold can be 10.The caching period of above-mentioned first caching can equally implement
When, according to the sets itselfs such as demand and/or system performance are realized, the present embodiment is to the length of the caching period of the above-mentioned first caching
It is not construed as limiting, for example, the caching period of above-mentioned first caching can be 5 seconds.
Writing module 34, for performing write operation to the write operation requests in the above-mentioned first caching.
In above-mentioned data transfer apparatus, after receiving module 31 receives the write operation requests that application is sent, module 32 is stored in
First by the first caching of the write operation requests received deposit, when the type of above-mentioned write operation requests is returned or write and together to write immediately
During step operation or when the above-mentioned first caching has met caching switching condition, handover module 33 will preserve the write operation received
The caching of request is switched to the second caching by the first caching, then by writing module 34 to the write operation requests in the above-mentioned first caching
Write operation is performed, so as to give full play to batch read-write and the concurrency of writing disk manipulation, and then can not influence to apply
Maximum performance handling capacity is improved on the premise of write operation semanteme.
Fig. 4 is the structure diagram of another embodiment of data transfer apparatus of the present invention, writes and fills with data shown in Fig. 3
It puts and compares, the difference is that, data transfer apparatus shown in Fig. 4 can also include：Write disk module 35；
Wherein, disk module 35 is write, for working as the type of above-mentioned write operation requests to write and simultaneously operating or met same
During step operation trigger condition, writing module 34 is performed into the data that write operation write and is stored in disk.That is, when reception
The type for the write operation requests that module 31 receives for write and sync operate when or ought meet sync operate trigger condition
When, it can not only trigger handover module 33 and writing module 34 performs corresponding operation, also trigger and write the execution of disk module 35 sync
Semantic brush will perform the data that write operation write and be stored in disk.
Wherein, having met sync operations trigger condition can be：The data entry that write operation is write is performed to have reached
The caching period of second threshold and/or above-mentioned first caching has timed out.The size of above-mentioned second threshold can implement
When, according to the sets itselfs such as demand and/or system performance are realized, the present embodiment is not construed as limiting the size of second threshold, illustrates
For, above-mentioned second threshold can be 30.In the present embodiment, after handover module 33 carries out caching switching, writing module 34 is right
Write operation requests in the first caching switched perform write operation, the write operation requests institute for simply preserving the first caching
The data entry of carrying writes another level cache, such as：The data entry entrained by write operation requests that buffer is preserved is write
Enter cache, the data entry entrained by above-mentioned write operation requests is not write into disk.In the number that execution write operation is write
The caching period for having reached second threshold and/or the first caching according to entry has timed out that (this means current cache through a long times
Do not write data) in the case of, it can just trigger and write the execution sync semanteme brushs of disk module 35, the execution of writing module 34 is write
Enter the write data deposit disk of operation.
In addition, as previously mentioned, when the write operation requests that receiving module 31 receives type for write and sync operate when, no
Whether pipe first has request or how many request in caching, can trigger handover module 33 immediately and writing module 34 performs phase
The operation answered, and perform sync semanteme brushs by writing disk module 35 will perform the data that write operation write and be stored in disk.
Further, above-mentioned data transfer apparatus can also include：
Sending module 36, after performing write operation to the write operation requests in the first caching in writing module 34,
Write operation response is returned to above application, with to the completion status of the above-mentioned write operation of above-mentioned applicative notifications.That is, this reality
It applies in example, the write operation requests in the first caching that writing module 34 switches handover module 33 perform batch write operation,
The return of write request is just called after being finished, write operation response is returned from sending module 36 to above application, to be answered to above-mentioned
With the completion status for notifying above-mentioned write operation.
Above-mentioned data transfer apparatus can give full play to batch read-write and the concurrency of writing disk manipulation, and then can be in not shadow
Maximum performance handling capacity is improved on the premise of response write operation semanteme.
It should be noted that in the description of the present invention, term " first ", " second " etc. are only used for description purpose, without
It is understood that indicate or imply relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
It is two or more.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, segment or the portion of the code of the executable instruction of one or more the step of being used to implement specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.If for example, with hardware come realize in another embodiment, can be under well known in the art
Any one of row technology or their combination are realized：With for the logic gates to data-signal realization logic function
Discrete logic, have suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array
(Programmable Gate Array；Hereinafter referred to as：PGA), field programmable gate array (Field Programmable
Gate Array；Hereinafter referred to as：FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, one or a combination set of the step of including embodiment of the method.
In addition, each function module in each embodiment of the present invention can be integrated in a processing module or
Modules are individually physically present, can also two or more modules be integrated in a module.Above-mentioned integrated module
Both the form that hardware may be employed is realized, can also be realized in the form of software function module.If the integrated module
In the form of software function module realize and be independent production marketing or in use, a computer can also be stored in can
It reads in storage medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment of the present invention or example.In the present specification, schematic expression of the above terms is not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiments or example in combine in an appropriate manner.
Although the embodiment of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of method for writing data, which is characterized in that including：
Receive the write operation requests that application is sent；
By the first caching of write operation requests deposit；
When the type of the write operation requests is returned or write and during simultaneously operating or when the described first caching has been expired to write immediately
During other caching switching conditions of foot, the caching for preserving the write operation requests received is switched to second by the described first caching and is delayed
It deposits；
Write operation is performed to the write operation requests in the described first caching；
Wherein, performing write operation to the write operation requests in the described first caching includes：It is write what the described first caching preserved
Data entry entrained by operation requests writes another level cache.
2. according to the method described in claim 1, it is characterized in that, first caching has met other caching switching condition bags
It includes：The item number of write operation requests cached in first caching reach first threshold and/or, the caching of first caching
Cycle has timed out.
3. method according to claim 1 or 2, which is characterized in that further include：
When the type of the write operation requests to write and simultaneously operating or when having met simultaneously operating trigger condition, will perform
The data deposit disk that write operation is write.
4. according to the method described in claim 3, it is characterized in that, the simultaneously operating trigger condition that met includes：It performs
The data entry that write operation is write has reached second threshold and/or the caching period of first caching has timed out.
5. method according to claim 1 or 2, which is characterized in that the write operation requests in the described first caching
After performing write operation, further include：
Write operation response is returned to the application, with the completion status operated to the applicative notifications said write.
6. a kind of data transfer apparatus, which is characterized in that including：
Receiving module, for receiving the write operation requests that application is sent；
Module is stored in, for the first caching of write operation requests deposit for receiving the receiving module；
Handover module, for returning or writing immediately and during simultaneously operating or work as institute to write when the type of the write operation requests
When stating the first caching and having met other caching switching conditions, the caching of write operation requests that receives will be preserved and cached by described first
It is switched to the second caching；
Writing module, for performing write operation to the write operation requests in the described first caching；
Wherein, said write module, specifically for caching the data entry entrained by the write operation requests preserved by described first
Write another level cache.
7. device according to claim 6, which is characterized in that first caching has met other caching switching condition bags
It includes：The item number of write operation requests cached in first caching reach first threshold and/or, the caching of first caching
Cycle has timed out.
8. the device according to claim 6 or 7, which is characterized in that further include：
Write disk module, for work as the type of the write operation requests for write and simultaneously operating or met simultaneously operating triggering
During condition, the data that the execution write operation of said write module is write are stored in disk.
9. device according to claim 8, which is characterized in that the simultaneously operating trigger condition that met includes：It performs
The data entry that write operation is write has reached second threshold and/or the caching period of first caching has timed out.
10. the device according to claim 6 or 7, which is characterized in that further include：
Sending module, after performing write operation to the write operation requests in the described first caching in said write module,
Write operation response is returned to the application, with the completion status operated to the applicative notifications said write.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510146467.1A CN104731533B (en) | 2015-03-31 | 2015-03-31 | Method for writing data and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510146467.1A CN104731533B (en) | 2015-03-31 | 2015-03-31 | Method for writing data and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104731533A CN104731533A (en) | 2015-06-24 |
| CN104731533B true CN104731533B (en) | 2018-06-05 |
Family
ID=53455467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510146467.1A Active CN104731533B (en) | 2015-03-31 | 2015-03-31 | Method for writing data and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104731533B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918381B (en) * | 2019-03-13 | 2021-06-11 | 北京百度网讯科技有限公司 | Method and apparatus for storing data |
| CN112748861A (en) * | 2019-10-31 | 2021-05-04 | 伊姆西Ip控股有限责任公司 | Method, electronic device and computer program product for providing information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102497450A (en) * | 2011-12-28 | 2012-06-13 | 北京华电天仁电力控制技术有限公司 | Two-stage-system-based distributed data compression processing method |
| CN103064929A (en) * | 2012-12-24 | 2013-04-24 | 创新科存储技术（深圳）有限公司 | Method for server writing data in network file system |
| CN103218174A (en) * | 2013-03-29 | 2013-07-24 | 航天恒星科技有限公司 | IO (Input Output) double-buffer interactive multicore processing method for remote sensing image |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007122221A (en) * | 2005-10-26 | 2007-05-17 | Sony Corp | Information processor, information processing method and computer program |
| CN101136710B (en) * | 2006-10-25 | 2011-06-22 | 中兴通讯股份有限公司 | Data storage control method of virtual cascade recover |
| CN101923442B (en) * | 2009-06-09 | 2012-05-23 | 英业达集团(天津)电子技术有限公司 | Caching data synchronous system and method in process of accessing iSCSI (Internet Small Computer System Interface) storage device |
-
2015
- 2015-03-31 CN CN201510146467.1A patent/CN104731533B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102497450A (en) * | 2011-12-28 | 2012-06-13 | 北京华电天仁电力控制技术有限公司 | Two-stage-system-based distributed data compression processing method |
| CN103064929A (en) * | 2012-12-24 | 2013-04-24 | 创新科存储技术（深圳）有限公司 | Method for server writing data in network file system |
| CN103218174A (en) * | 2013-03-29 | 2013-07-24 | 航天恒星科技有限公司 | IO (Input Output) double-buffer interactive multicore processing method for remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104731533A (en) | 2015-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104461391B (en) | A kind of storage device metadata management approach and system | |
| CN107423422A (en) | Spatial data distributed storage and search method and system based on grid | |
| CN104216773B (en) | View switching method and apparatus | |
| CN105224255B (en) | A kind of storage file management method and device | |
| CN105808643A (en) | Redis memory database refreshing method | |
| CN107798130A (en) | A kind of Snapshot Method of distributed storage | |
| CN106325758B (en) | A kind of queue storage space management method and device | |
| CN104731533B (en) | Method for writing data and device | |
| CN102043593B (en) | Region-based management method for external cache of disk | |
| CN104133783B (en) | Method and device for processing distributed cache data | |
| WO2020147253A1 (en) | Data read/write method and apparatus, and exchange chip and storage medium | |
| CN103514274A (en) | Method for data migration of non-relational database HBase | |
| CN104035703A (en) | Client side, method and system for changing view display | |
| US10387308B2 (en) | Method and apparatus for online reducing caching devices | |
| CN106294768A (en) | Information search method and information search engine | |
| CN107111461A (en) | Bandwidth of memory is provided using back-to-back read operation in the system based on CPU (CPU) by compressed Memory Controller (CMC) to compress | |
| CN109388341A (en) | A kind of system storage optimization method based on Device Mapper | |
| CN109614044A (en) | A kind of processing method, device and the equipment of solid state hard disk write error | |
| CN109783258A (en) | A kind of message treatment method, device and server | |
| CN105302493B (en) | The swapping in and out control method and system that SSD is cached in a kind of mixing storage array | |
| CN106951182A (en) | A kind of block device caching method and device | |
| CN106254270A (en) | A kind of queue management method and device | |
| CN104808950B (en) | Modal dependence access to in-line memory element | |
| CN104834478B (en) | A kind of data write-in and read method based on isomery mixing storage device | |
| CN105630413B (en) | A kind of synchronization write-back method of data in magnetic disk |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |