CN106020718A - A method and a system for improving virtual disk write-in performance - Google Patents
A method and a system for improving virtual disk write-in performance Download PDFInfo
- Publication number
- CN106020718A CN106020718A CN201610300590.9A CN201610300590A CN106020718A CN 106020718 A CN106020718 A CN 106020718A CN 201610300590 A CN201610300590 A CN 201610300590A CN 106020718 A CN106020718 A CN 106020718A
- Authority
- CN
- China
- Prior art keywords
- data
- write
- node
- length
- virtual disk
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0667—Virtualisation aspects at data level, e.g. file, record or object virtualisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/0674—Disk device
- G06F3/0676—Magnetic disk device
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention relates to the field of virtual disks and in particular provides a method and a system for improving virtual disk write-in performance. The data write-in speed can be increased by creating mapping tables in the cache of a memory. Compared with conventional virtual disk write-in method, the method employs a mapping table including nodes; the data total length of a cache is preset; every time a cache is newly added, the data total length of the caches of the mapping table can be updated; when the length exceeds a preset threshold value, data written into the caches of the mapping table are written into a virtual disk file at one time, so that the problem that a cursor frequently moves and updates positions is solved and the virtual disk write-in performance is improved.
Description
Technical field
The present invention relates to virtual disk field, particularly relate to a kind of method improving virtual disk write performance and
System.
Background technology
In virtual disk, virtual disk is read and write the read-write operation really to local disk file.?
The virtual disk files only one of which vernier pointer of application layer, the position every time updating vernier pointer all can have one
The delay fixed time, when in the case of data volume is more compared with the quantity of documents that big and virtual disk preserve, remembers
Recording different files will make vernier pointer do location updating frequently in virtual disk files, thus affects
The write performance of virtual disk.Read-write especially when multithreading accesses virtual disk simultaneously, to virtual disk
Operation will be substantially reduced the write performance of virtual disk.
In the file system of existing operating system, each file is the vernier pointer having correspondence, should
When accessing file with layer, the vernier pointer of this file is independent, will not be disturbed by other file operation,
The vernier pointer of file can be moved by the order of written document.Owing to virtual disk is on local hard drive
File, can record a lot of file datas, and virtual disk is a literary composition in file system in this file
Part, also only one of which vernier pointer, virtual disk is in order to realize and the multiple files in file system, it is necessary to
The vernier pointer of multiple files is simulated, with a multiple file of file analogy at virtual magnetic by a vernier pointer
Storage in dish.
Such as: the data of the multiple file of virtual disk are placed on the diverse location of same file, when opening
When one file writes, the vernier pointer of virtual disk will move to the start bit that this file is deposited
Put and write.When multiple files carry out write operation in different threads, each thread is actually
Moving the vernier pointer of same file (i.e. virtual disk), such as thread 1 is from the A of virtual disk
Position written document, thread 2 will be from the B location written document of virtual disk, when thread 1 writes N number of byte,
Thread 2 starts to write, and at this moment vernier will move to B location from A+N position, and two thread contentions are same
The access right of file, this has resulted in the frequent mobile of file vernier pointer, and then has affected writing of virtual disk
Enter performance.
Summary of the invention
The technical problem to be solved is: provide a kind of when quantity of documents is many and data volume is big, energy
Enough reduce the vernier of virtual disk files frequently move update position improve virtual disk write performance
Method and system.
In order to solve above-mentioned technical problem, the technical solution used in the present invention is:
A kind of method improving virtual disk write performance, including:
Step 1, in the caching of internal memory create mapping table, described mapping table includes node；The number of preset buffer memory
According to total length；
Step 2, write data to described node, update the total length of data of caching；
Step 3, when caching total length of data exceed default threshold value time, will write described node data one
Secondary property writes to virtual disk files.
Another technical scheme that the present invention uses is:
A kind of system improving virtual disk write performance, including creation module, more new module and writing module；
Described creation module, for creating mapping table in the caching of internal memory, described mapping table includes node；
The total length of data of preset buffer memory；
Described more new module, is used for writing data to described node, updates the total length of data of caching；
Said write module, for when the total length of data of caching exceedes default threshold value, by described for write
The data one-time write of node is in virtual disk files.
Traditional virtual disk writing mode: when virtual disk processes multifile, namely will be to multifile
Carrying out vernier repeatedly to move, vernier frequently moves renewal position.
The beneficial effects of the present invention is: by creating mapping table in the caching of internal memory, data can be improved
Writing speed；Compared with traditional virtual disk writing mode, technical scheme uses a mapping table,
It includes node, and the total length that the total length of data of preset buffer memory is data cached, when the most newly-increased caching,
The total length of data of the caching of mapping table all can be updated, when its length exceedes default threshold value, and can handle
The data of the upper write of caching in mapping table are disposably written in virtual disk files, thus reduce vernier
Frequently move renewal position, and then improve virtual disk write performance.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of method improving virtual disk write performance of the present invention；
Fig. 2 is the structured flowchart of a kind of system improving virtual disk write performance of the present invention；
Fig. 3 is the flow chart of the method improving virtual disk write performance of embodiments of the invention one；
Label declaration:
1, creation module；2, more new module；3, writing module.
Detailed description of the invention
By describing the technology contents of the present invention in detail, being realized purpose and effect, below in conjunction with embodiment also
Accompanying drawing is coordinated to be explained.
The design of most critical of the present invention is: use a mapping table, and it includes node, and the number of preset buffer memory
According to total length, when the most newly-increased caching, the length of mapping table node all can obtain with the total length of data of caching
To updating, when its length exceedes default threshold value, the caching in mapping table disposably can be written to void
Intend in disk file, thus reduce vernier and frequently move renewal position, and then improve virtual disk write
Performance.
Refer to Fig. 1, a kind of method improving virtual disk write performance that the present invention provides, including:
Step 1, in the caching of internal memory create mapping table, described mapping table includes node；The number of preset buffer memory
According to total length；
Step 2, write data to described node, update the total length of data of caching；
Step 3, when caching total length of data exceed default threshold value time, will write described node data one
Secondary property writes to virtual disk files.
Knowable to foregoing description, the beneficial effects of the present invention is: map by creating in the caching of internal memory
Table, can improve the writing speed of data；Compared with traditional virtual disk writing mode, the technology of the present invention
Scheme uses a mapping table, and it includes node, and the total length that the total length of data of preset buffer memory is data cached,
When the most newly-increased caching, the total length of data of the caching of mapping table all can be updated, when its length exceedes
During the threshold value preset, the data of upper for the caching in mapping table write disposably can be written to virtual disk literary composition
In part, thus reduce vernier and frequently move renewal position, and then improve virtual disk write performance.
Further, described node by store the write initial address of virtual disk files, the length of node and
The data composition of write.
Further, described step 2 specifically includes step 21-step 26:
The data space model whether step 21, inquiry current write address are stored at the node of described mapping table
In enclosing；If so, the primary nodal point that described current write address is corresponding is obtained；If it is not, increase new node also
After being inserted into previous node, the length of more new node and the total length of data of caching, re-execute step 21；
Described node includes primary nodal point；
The length of the data that step 22, judgement currently need to write is the longest beyond original data in primary nodal point
Degree scope, if so, enters step 23；
Data length needed for step 23, the data being calculated write, it is judged that the end ground after write data
Location, whether beyond the length data scope in primary nodal point, if so, enters step 24；If it is not, entrance step
25；
Step 24, using the next node of primary nodal point as new primary nodal point, return step 22；
Step 25, according to step 23 be calculated write data needed for data length increase data space, will
The data space increased inserts in primary nodal point, the length of more new node and the total length of data of caching；
Step 26, start to write data from the current write address described in step 21.
Seen from the above description, before write data, whether first inquiry needs the data address of write original
Spatial cache in, (be increase node if it was not then need to increase new spatial cache or increase number
According to space)；If in original spatial cache, at this time prepare data to be write, but in view of original
Spatial cache internal memory contains part data, and this allows for the covering problem to legacy data, it is therefore desirable to first
Judge to need the covering problem of data and the legacy data of write, if the length of data currently need to be write beyond the
One node's length scope, then need to judge the length whether end address after writing data exceeds next node again
Degrees of data scope, if without departing from, then supplemental data space depositing again after covering；If exceeding, then need to sentence
Disconnected next node.
Further, described step 22 also includes: if the length of the data that currently need to write is without departing from first segment
In point, original data length scope, then start to write data from the current write address described in step 21.
Seen from the above description, if the length of the data that currently need to write is original without departing from primary nodal point data
Data length scope, then data of can writing direct.
Refer to Fig. 2, present invention also offers a kind of system improving virtual disk write performance, including creating
Module 1, more new module 2 and writing module 3；
Described creation module 1, for creating mapping table in the caching of internal memory, described mapping table includes node；
The total length of data of preset buffer memory；
Described more new module 2, is used for writing data to described node, updates the total length of data of caching；
Said write module 3, for when the total length of data of caching exceedes default threshold value, by described for write
The data one-time write of node is in virtual disk files.
Knowable to foregoing description, the beneficial effects of the present invention is: map by creating in the caching of internal memory
Table, can improve the writing speed of data；Compared with traditional virtual disk writing mode, the technology of the present invention
Scheme uses a mapping table, and it includes node, and the total length that the total length of data of preset buffer memory is data cached,
When the most newly-increased caching, the total length of data of the caching of mapping table all can be updated, when its length exceedes
During the threshold value preset, the data of upper for the caching in mapping table write disposably can be written to virtual disk literary composition
In part, thus reduce vernier and frequently move renewal position, and then improve virtual disk write performance.
Further, described node by store the write initial address of virtual disk files, the length of node and
The data composition of write.
Further, described more new module 2 includes query unit, judging unit, computing unit, return list
Unit, insertion unit and writing unit；
Described query unit, for inquiring about what whether current write address was stored at the node of described mapping table
In data space ranges；If so, the primary nodal point that described current write address is corresponding is obtained；If it is not, increase
New node after being inserted into previous node, the length of more new node and the total length of data of caching, again
Perform query unit；Described node data includes primary nodal point；
Described judging unit, for judging that whether the length of the data that currently need to write is beyond primary nodal point Central Plains
Some data length scopes, if so, enter computing unit；
Described computing unit, for being calculated the data length needed for the data of write, it is judged that write data
After end address whether beyond the length data scope in primary nodal point, if so, enter and return unit；If
No, enter and insert unit；
Described return unit, for sentencing the next node of primary nodal point as new primary nodal point, return
Disconnected unit；
Described insertion unit, the data length needed for be calculated write data according to computing unit increases
Data space, inserts in primary nodal point by the data space increased, the length of more new node and the number of caching
According to total length；
Said write unit, for starting to write data from described current write address.
Seen from the above description, before write data, whether first inquiry needs the data address of write original
Spatial cache in, if it was not then need to increase new spatial cache (to be increase node data or increasing
Add data space)；If in original spatial cache, at this time prepare data to be write, but in view of former
Some spatial cache internal memories contain part data, and this allows for the covering problem to legacy data, therefore needs
First to judge the covering problem of data and the legacy data needing write, if the length that currently need to write data surpasses
Go out original data length scope in primary nodal point, then need whether to judge the end address after writing data again
Beyond the length data scope of next node, if without departing from, then supplemental data space depositing again after covering；
If exceeding, then need to judge the length whether primary nodal point length exceedes next node.
Further, described judging unit, if the length of data being additionally operable to currently need to write is without departing from first
In node, original data length scope, then start to write data from described current write address.
Seen from the above description, if the length that currently need to write data is original without departing from primary nodal point data
Data length scope, then data of can writing direct.
Refer to Fig. 1-3, embodiments of the invention one are:
A kind of method improving virtual disk write performance that the present invention provides, including:
Step 1, in the caching of internal memory create mapping table, described mapping table includes node；The number of preset buffer memory
According to total length；Described node is by storing the write initial address of virtual disk files, the length of node and write
Data composition.When virtual initialization, initialize mapping table and the total length of data of mapping table storage, reflect
Each node in firing table preserves starting writing position and writing the length of data of the file of virtual disk,
Can be mapped in a caching chained list by each node.The i.e. corresponding caching chain of the file of each virtual disk
Table.
Wherein write initial address is position 1 in table 1, position 2 ..., position N；
Wherein the length data of storage write data is length 1, length 2 ..., length N；
Table 1
Step 2, write data to the length of described node, more new node and the total length of data of caching；
Before write data, first whether the data address of inquiry needs write is in original spatial cache, as
Fruit does not exists, then need to increase new spatial cache (be increase node data or increase data space)；If
In original spatial cache, at this time prepare data to be write, but in view of original spatial cache internal memory
Containing part data, this allows for the covering problem to legacy data, it is therefore desirable to first judge to need write
The covering problem of data and legacy data, if the length of data currently need to be write beyond original in primary nodal point
Data length scope, then need to judge again that the end address after writing data is whether beyond the length number of node
According to scope, if without departing from, then supplemental data space depositing again after covering；If exceeding, then need to judge
The next node of one node.
Before file writes, first can inquire about in the mapping table according to the position of file, can return slow after finding
Deposit the pointer of chained list.Here inquiry is that the document location specified is preserved either with or without at certain node of mapping table
Data space ranges in.I.e. specify starting position and the end position in the whether hiting data district, position of lookup
Between.If hitting in already present data field, return the mapping table node address found.
Described step 2 specifically includes step 21-step 26:
The data space model whether step 21, inquiry current write address are stored at the node of described mapping table
In enclosing；If so, the primary nodal point that described current write address is corresponding is obtained；If it is not, increase new node also
After being inserted into previous node, the length of more new node and the total length of data of caching, re-execute step 21；
Described node includes primary nodal point；
The length of the data that step 22, judgement currently need to write is the longest beyond original data in primary nodal point
Degree scope, if so, enters step 23；
Data length needed for step 23, the data being calculated write, it is judged that the end ground after write data
Location, whether beyond the length data scope in primary nodal point, if so, enters step 24；If it is not, entrance step
25；
Step 24, using the next node of primary nodal point as new primary nodal point, return step 22；
Step 25, according to step 23 be calculated write data needed for data length increase data space, will
The data space increased inserts in primary nodal point, the length of more new node and the total length of data of caching；
Step 26, start to write data from the current write address described in step 21.
Refering to Fig. 3, specific as follows:
Just apply for new mapping table node if 1 node is sky and is inserted in mapping table.
2, the value recalculating LEN1 again is LEN1 ＇.(POS1 preservation is that file vernier starts write
Position, LEN1 represents the data length value to be write with the program of POS1 correspondence position)
3, judge whether LEN1 ＇+POS1 (slider position that present node is corresponding) value exceedes mapping table
Next node position.
4 if it does, current mapping table node motion is to next node, and performs F；
If 5 are less than, the subprogram that the data that the node of POS1 position starts to deposit exceed can be again
Application space, and insert after write in the data link table of POS1 place mapping table node；
If 6 find node address, then judge that whether data to be covered are beyond legacy data space；
7, exceed, perform 2；
8, it is less than, then covers the data of data field opposite position；
9, after data write, the total length of the data of mapping table storage is updated；
Cover the data of data field opposite position.Such as: position to be write is POS2, at mapping table
Present node position is POS1, when POS2 is less than or equal to POS1+LEN1 more than or equal to POS1, then
Write operation is to cover the data in data field.(such as table 2)
Table 2
Step 3, when caching total length of data exceed default threshold value time, by write node data disposable
Write to virtual disk files.
In sum, a kind of method and system improving virtual disk write performance that the present invention provides, pass through
In the caching of internal memory, create mapping table, the writing speed of data can be improved；With traditional virtual disk write
Mode is compared, and technical scheme uses a mapping table, and it includes node, and the data of preset buffer memory
The total length that total length is data cached, when the most newly-increased caching, the total length of data of the caching of mapping table is all
Can be updated, when its length exceedes default threshold value, can be the data of upper for the caching in mapping table write
Disposably it is written in virtual disk files, thus reduces vernier and frequently move renewal position, and then
Improve virtual disk write performance.
The foregoing is only embodiments of the invention, not thereby limit the scope of the claims of the present invention, every profit
The equivalents made by description of the invention and accompanying drawing content, or directly or indirectly it is used in relevant technology
Field, is the most in like manner included in the scope of patent protection of the present invention.
Claims (8)
1. the method improving virtual disk write performance, it is characterised in that including:
Step 1, in the caching of internal memory create mapping table, described mapping table includes node；The number of preset buffer memory
According to total length；
Step 2, write data to described node, update the total length of data of caching；
Step 3, when caching total length of data exceed default threshold value time, will write described node data one
Secondary property writes to virtual disk files.
The method of raising virtual disk write performance the most according to claim 1, it is characterised in that institute
State node to be made up of the data storing the write initial address of virtual disk files, the length of node and write.
The method of raising virtual disk write performance the most according to claim 2, it is characterised in that institute
State step 2 and specifically include step 21-step 26:
The data space model whether step 21, inquiry current write address are stored at the node of described mapping table
In enclosing；If so, the primary nodal point that described current write address is corresponding is obtained；If it is not, increase new node also
After being inserted into previous node, the length of more new node and the total length of data of caching, re-execute step 21；
Described node includes primary nodal point；
The length of the data that step 22, judgement currently need to write is the longest beyond original data in primary nodal point
Degree scope, if so, enters step 23；
Data length needed for step 23, the data being calculated write, it is judged that the end ground after write data
Location, whether beyond the length data scope in primary nodal point, if so, enters step 24；If it is not, entrance step
25；
Step 24, using the next node of primary nodal point as new primary nodal point, return step 22；
Step 25, according to step 23 be calculated write data needed for data length increase data space, will
The data space increased inserts in primary nodal point, the length of more new node and the total length of data of caching；
Step 26, start to write data from the current write address described in step 21.
The method of raising virtual disk write performance the most according to claim 3, it is characterised in that institute
State step 22 also to include: if the length of the data that currently need to write is without departing from primary nodal point, original data are long
Degree scope, then start to write data from the current write address described in step 21.
5. the system improving virtual disk write performance, it is characterised in that include creation module, renewal
Module and writing module；
Described creation module, for creating mapping table in the caching of internal memory, described mapping table includes node；
The total length of data of preset buffer memory；
Described more new module, is used for writing data to described node, updates the total length of data of caching；
Said write module, for when the total length of data of caching exceedes default threshold value, by described for write
The data one-time write of node is in virtual disk files.
The system of raising virtual disk write performance the most according to claim 5, it is characterised in that institute
State node to be made up of the data storing the write initial address of virtual disk files, the length of node and write.
The system of raising virtual disk write performance the most according to claim 6, it is characterised in that institute
State more new module to include query unit, judging unit, computing unit, return unit, insert unit and write
Unit；
Described query unit, for inquiring about what whether current write address was stored at the node of described mapping table
In data space ranges；If so, the primary nodal point that described current write address is corresponding is obtained；If it is not, increase
New node after being inserted into previous node, the length of more new node and the total length of data of caching, again
Perform query unit；Described node data includes primary nodal point；
Described judging unit, for judging that whether the length of the data that currently need to write is beyond primary nodal point Central Plains
Some data length scopes, if so, enter computing unit；
Described computing unit, for being calculated the data length needed for the data of write, it is judged that write data
After end address whether beyond the length data scope in primary nodal point, if so, enter and return unit；If
No, enter and insert unit；
Described return unit, for sentencing the next node of primary nodal point as new primary nodal point, return
Disconnected unit；
Described insertion unit, the data length needed for be calculated write data according to computing unit increases
Data space, inserts in primary nodal point by the data space increased, the length of more new node and the number of caching
According to total length；
Said write unit, for starting to write data from described current write address.
The system of raising virtual disk write performance the most according to claim 7, it is characterised in that institute
State judging unit, if be additionally operable to the length of data that currently need to write without departing from primary nodal point original data
Length range, then start to write data from described current write address.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610300590.9A CN106020718A (en) | 2016-05-09 | 2016-05-09 | A method and a system for improving virtual disk write-in performance |
| PCT/CN2016/092810 WO2017193488A1 (en) | 2016-05-09 | 2016-08-02 | Method and system for improving write performance of virtual disk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610300590.9A CN106020718A (en) | 2016-05-09 | 2016-05-09 | A method and a system for improving virtual disk write-in performance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106020718A true CN106020718A (en) | 2016-10-12 |
Family
ID=57098810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610300590.9A Pending CN106020718A (en) | 2016-05-09 | 2016-05-09 | A method and a system for improving virtual disk write-in performance |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106020718A (en) |
| WO (1) | WO2017193488A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832017A (en) * | 2017-11-14 | 2018-03-23 | 中国石油集团川庆钻探工程有限公司地球物理勘探公司 | A kind of method and device for improving geological data storage IO performances |
| CN107861685A (en) * | 2017-06-20 | 2018-03-30 | 平安科技（深圳）有限公司 | Virtual disk wiring method and device, storage medium based on copy-on-write |
| CN109831508A (en) * | 2019-02-15 | 2019-05-31 | 网宿科技股份有限公司 | A kind of caching method and equipment, storage medium |
| CN110543495A (en) * | 2019-08-29 | 2019-12-06 | 北京东方国信科技股份有限公司 | cursor traversal storage method and device |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111399781B (en) * | 2020-04-21 | 2023-09-19 | 中国科学院光电技术研究所 | Storage method for improving reliability of real-time image recording system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102087586A (en) * | 2009-12-02 | 2011-06-08 | 成都市华为赛门铁克科技有限公司 | Data processing method and device |
| CN102763070A (en) * | 2011-11-01 | 2012-10-31 | 华为技术有限公司 | Method and device for managing disk cache |
| CN103049219A (en) * | 2012-12-12 | 2013-04-17 | 华中科技大学 | Virtual disk write cache system applicable to virtualization platform and operation method of write cache system |
| CN103186617A (en) * | 2011-12-30 | 2013-07-03 | 北京新媒传信科技有限公司 | Data storage method and device |
| CN105159604A (en) * | 2015-08-20 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Disk data read-write method and system |
| CN105469001A (en) * | 2014-08-15 | 2016-04-06 | 中兴通讯股份有限公司 | Disk data protection method and device |
-
2016
- 2016-05-09 CN CN201610300590.9A patent/CN106020718A/en active Pending
- 2016-08-02 WO PCT/CN2016/092810 patent/WO2017193488A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102087586A (en) * | 2009-12-02 | 2011-06-08 | 成都市华为赛门铁克科技有限公司 | Data processing method and device |
| CN102763070A (en) * | 2011-11-01 | 2012-10-31 | 华为技术有限公司 | Method and device for managing disk cache |
| CN103186617A (en) * | 2011-12-30 | 2013-07-03 | 北京新媒传信科技有限公司 | Data storage method and device |
| CN103049219A (en) * | 2012-12-12 | 2013-04-17 | 华中科技大学 | Virtual disk write cache system applicable to virtualization platform and operation method of write cache system |
| CN105469001A (en) * | 2014-08-15 | 2016-04-06 | 中兴通讯股份有限公司 | Disk data protection method and device |
| CN105159604A (en) * | 2015-08-20 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Disk data read-write method and system |
Non-Patent Citations (1)
| Title |
|---|
| 王绪洪: "虚拟化环境下的虚拟磁盘写缓存机制研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107861685A (en) * | 2017-06-20 | 2018-03-30 | 平安科技（深圳）有限公司 | Virtual disk wiring method and device, storage medium based on copy-on-write |
| CN107832017A (en) * | 2017-11-14 | 2018-03-23 | 中国石油集团川庆钻探工程有限公司地球物理勘探公司 | A kind of method and device for improving geological data storage IO performances |
| CN109831508A (en) * | 2019-02-15 | 2019-05-31 | 网宿科技股份有限公司 | A kind of caching method and equipment, storage medium |
| CN109831508B (en) * | 2019-02-15 | 2021-11-19 | 网宿科技股份有限公司 | Caching method and equipment and storage medium |
| CN110543495A (en) * | 2019-08-29 | 2019-12-06 | 北京东方国信科技股份有限公司 | cursor traversal storage method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017193488A1 (en) | 2017-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106020718A (en) | A method and a system for improving virtual disk write-in performance | |
| US10282122B2 (en) | Methods and systems of a memory controller for hierarchical immutable content-addressable memory processor | |
| CN105574104B (en) | A kind of LogStructure storage system and its method for writing data based on ObjectStore | |
| US7594067B2 (en) | Enhanced data access in a storage device | |
| CN102349055B (en) | To the access time optimization of the file stored on a memory | |
| US10740251B2 (en) | Hybrid drive translation layer | |
| US8171219B2 (en) | Method and system to perform caching based on file-level heuristics | |
| US5008820A (en) | Method of rapidly opening disk files identified by path names | |
| CN103838853B (en) | Mixed file system based on different storage media | |
| US20030101327A1 (en) | Flash memory management method | |
| US9507705B2 (en) | Write cache sorting | |
| CN107784121A (en) | Lowercase optimization method of log file system based on nonvolatile memory | |
| CN103365786B (en) | Date storage method, device and system | |
| Lee et al. | An efficient index buffer management scheme for implementing a B-tree on NAND flash memory | |
| CN107368436A (en) | A kind of cold and hot data separating storage method of flash memory for combining address mapping table | |
| WO2018096322A1 (en) | Data movement engine | |
| CN105260139B (en) | A kind of disk management method and system | |
| CN102650972B (en) | Date storage method, Apparatus and system | |
| US20100281082A1 (en) | Subordinate Multiobjects | |
| CN108491166B (en) | Read data cache management method for optical disk library | |
| CN112148639A (en) | High-efficiency small-capacity cache memory replacement method and system | |
| US11086798B2 (en) | Method and computer program product and apparatus for controlling data access of a flash memory device | |
| CN106990917A (en) | File read/write method and system | |
| Lee et al. | On Flash-Based DBMSs: Issues for Architectural Re-Examination. | |
| Lee et al. | Research issues in next generation DBMS for mobile platforms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20161012 |