CN106354890A - Implementation method of random access file system based on N-ary tree structure - Google Patents
Implementation method of random access file system based on N-ary tree structure Download PDFInfo
- Publication number
- CN106354890A CN106354890A CN201611041427.1A CN201611041427A CN106354890A CN 106354890 A CN106354890 A CN 106354890A CN 201611041427 A CN201611041427 A CN 201611041427A CN 106354890 A CN106354890 A CN 106354890A
- Authority
- CN
- China
- Prior art keywords
- page
- file
- node
- data
- ary tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/13—File access structures, e.g. distributed indices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an implementation method of a random access file system based on an N-ary tree structure. The implementation method includes the steps that all file data in the file system are managed in the units of page; an iNode region and a data region are arranged in the file system, and the data region comprises a node page and a data page; an iNode node stored in the iNode region comprises an N-ary tree series field and an N-ary tree root node field; the number of the N<th> level node page corresponding to a file is used as a root node, the number of the (N-1)<th> level node page is used as the first level subnode, the rest can be done in the same manner, the number of the first level node page is used as the (N-1)<th> level subnode to form an N-ary tree to store and manage all the data of the file, wherein the first level node page is the data page, and the traversal sequence of the N-ary tree is the logic sequence of the data page. According to the implementation method of the random access file system based on the N-ary tree structure, random access of the file data in physical storage space is achieved, and the overall operation efficiency of the file system is improved to the maximum.
Description
Technical field
The present invention relates to the technical field of file system, more particularly to a kind of random access based on n-ary tree construction
File system implementation method.
Background technology
Development with the new memory technology such as nvdimm, 3d xpoint and ibm are to storage level internal memory (storage
Class memory, scm) framework proposition, research is become based on mixing memory system framework and non-volatile memory nvm of management
Focus.New memory technology scm has the features such as non-volatile, reading writes fast, low in energy consumption soon, but still has gap compared with dram,
The reliability that cycle life also reduces system is wiped in limited writing.In prior art, proposed excessive based on new memory technology scm
Plant memory organization mode and optimization method.
With the development of the technology such as big data, cloud computing, Internet of Things, data just constantly increasing at an unprecedented rate and
Accumulation.How to manage and organize these data, be a challenge for traditional file system.Although current file system
Provide a kind of easy-to-use Method of Data Organization for application, but this Method of Data Organization is to be set based on the hardware characteristicses of block device
Meter it is impossible to give full play to scm can random access performance characteristics.Therefore, how effectively to organize organization data, allow application program energy
Enough use in the way of closer to internal memory and access, and can keep that file system is reliable, easy care and the advantage such as shared, maximum
Changing ground raising system overall operation efficiency becomes problem demanding prompt solution.
Content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide a kind of based on n-ary tree construction
The implementation method of the file system of random access, manages the be stored in physical address of this document system using n-ary tree construction empty
Between data, realize random storage in amount of physical memory for the file data, and need not be by Documents Logical order physically
Location spatial order storage, thus substantially improve the overall operational efficiency of file system.
For achieving the above object and other related purposes, the present invention provides a kind of random access based on n-ary tree construction
File system implementation method, to manage all of file data of file system including in units of page;In file system
Setting data area of inode area, described data field includes node page data page, and described data page is used for storage file data,
Described node page is used for storing the physical address of next stage node page or data page in n-ary tree;Stored in described inode area
Inode node include n-ary tree level digital section and n-ary root vertex field, described n-ary tree level digital section is used for storing
The series of file adopted n-ary tree construction, described n-ary root vertex field is used for rising of n-th grade of node page of storage file
Beginning physical address;N-th grade of node page page number corresponding to file as root node, with (n-1) level node page page number for the 1st grade
Child node, by that analogy, with the 1st grade of node page page number for (n-1) level child node, forms a n-ary tree with to this document
All data carry out storage management;Wherein the 1st grade node page is data page;N-ary traversal of tree order is patrolling of data page
Collect order.
In one embodiment of the invention, described data page and described node page are in the mixing of described data field.
In one embodiment of the invention, described data page and described node page are dynamically distributes when to file write data
's;During to file write data, judging whether data page has existed according to writing address, if not existing, distributing data page,
And this data page of polishing is to required node page on path between root node.
In one embodiment of the invention, during file system establishment file, comprise the following steps:
One inode node of distribution;
The series n of the n-ary tree that specified file is adopted, is that file distributes n-th grade of node page;
The physical address of n-th grade of node page is write the n-ary root vertex field of file corresponding inode node;
The series n of the n-ary tree that file is adopted writes the n-ary tree level digital section in distributed inode node.
In one embodiment of the invention, in same file system, different files can have different n-ary trees
Series.
In one embodiment of the invention, the series of the n-ary tree that file is adopted can dynamically increase.
In one embodiment of the invention, dynamic the increased situation of series of the n-ary tree that triggering file is adopted includes:
Address during data is write by posix mode and surmounts current file logic length;
Current file logic length is surmounted when current location is positioned by file pointer;
By mmap mode by File Mapping to process virtual space when the length specified to have surmounted current file logic long
Degree.
In one embodiment of the invention, the series of the n-ary tree that file is adopted can dynamically increase and comprises the following steps:
File system obtains an idle node page as new root node from data field;
By first position of root node new for the physical address write of file primitive root node, and the thing by new root node
The series of the n-ary tree behind reason address and increase by 1 updates in the inode node of this document.
In one embodiment of the invention, the size of described page is in the same size with operating system memory page.
As described above, the implementation method of the file system of the random access based on n-ary tree construction of the present invention, have with
Lower beneficial effect:
(1) storage order in amount of physical memory based on n-ary tree construction file control data, realizes file data
Random storage in amount of physical memory, and need not be by Documents Logical order in physical address space sequential storage;
(2) manage the data of the be stored in physical address space of file system using n-ary tree construction, each file corresponds to
One n-ary tree construction, identical file system can achieve the file storage of the different capabilities rank such as 4k, 2m, 1g, meets to difference
The file data storage of capacity levels demand;
(3) the n-ary tree series adopting during file storage data is dynamically adapted, by dynamic adjustment file data
The n-ary tree series of management can achieve the upgrade expanding of file.
Brief description
Fig. 1 is shown as the framework of the implementation method of the file system of the random access based on n-ary tree construction of the present invention
Figure;
Fig. 2 is shown as the structural representation of inode node in the present invention;
Fig. 3 is shown as the structural representation of n-ary tree in the present invention;
Fig. 4 is shown as the n-ary tree construction and file data distribution feelings in data field in one embodiment of the present of invention
Condition schematic diagram;
Fig. 5 is shown as in one embodiment of the present of invention after write operation twice, file data page data field point
Cloth situation variation diagram;
Fig. 6 is shown as in one embodiment of the present of invention after write operation twice, the structure change of the n-ary tree of file
Figure.
Specific embodiment
Below by way of specific instantiation, embodiments of the present invention are described, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also be by addition different concrete realities
The mode of applying is carried out or applies, and the every details in this specification can also be based on different viewpoints and application, without departing from
Carry out various modifications and changes under the spirit of the present invention.It should be noted that, in the case of not conflicting, following examples and enforcement
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates the basic structure of the present invention in a schematic way
Think, then only show the assembly relevant with the present invention in schema rather than according to component count during actual enforcement, shape and size
Draw, during its actual enforcement, the kenel of each assembly, quantity and ratio can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
N-ary tree, cries n fork tree again, is a kind of common tree data structure, is usually used to complete the quick row of data
Sequence, data compression and quick-searching.N-ary tree has a root node, and the son node number of each node is identical.
The implementation method of the file system of the random access based on n-ary tree construction of the present invention adopts n-ary tree construction
The data of management the be stored in physical address space of file system, realizes file data depositing at random in amount of physical memory
Storage, and need not be by Documents Logical order in physical address space sequential storage.Based on n-ary tree construction, identical file system can
Realize the file storage of the different capabilities rank such as 4k, 2m, 1g.
The implementation method of the file system of the random access based on n-ary tree construction of the present invention is applied to dynamic random and deposits
Access to memory and the storage system of non-volatile RAM unified addressing.Wherein, non-volatile RAM includes phase
Transition storage, resistance-variable storing device, magnetic memory, ferroelectric memory etc..
With reference to Fig. 1, the implementation method of the file system of the random access based on n-ary tree construction of the present invention includes:
1) to manage all of file data of file system in units of page.
Preferably, the size of page and operating system memory page is in the same size.Generally, the data of 4k size is one page.Number
It is all 4k according to page, node page size, be simply divided into data page and node page because the content of storage is different.
2) data area of inode area is set in file system, data field includes node page (nodepage) data page
(datapage), data page is used for storage file data, and node page is used for storing next stage node page or data page in n-ary tree
Physical address;Data page and node page are in data field mixing;Inode node (the file control information being stored in inode area
Node) include inode nodes information field, n-ary tree level digital section and n-ary root vertex field, n-ary tree level digital section
For the series of storage file adopted n-ary tree construction, n-ary root vertex field is used for n-th grade of node page of storage file
nodepagenStart physical address;
Identical with prior art, the file system of the present invention includes superblock area, bit map area, data area of inode area.
As shown in Fig. 2 in inode area, each inode node increased n-ary on the basis of existing inode nodes information field
Tree level digital section and n-ary root vertex field.Wherein, inode nodes information field is used for the management information of storage file, such as
Founder, creation time, storing directory, authority etc.;N-ary tree level digital section is used for storage file adopted n-ary tree and ties
The series of structure;N-ary root vertex field is used for n-th grade of node page page of storage filenStart physical address.The number of the present invention
Also different from the data field of file system in prior art according to area.The page of the data field of the present invention is divided into node page data page.
Node page is used for storing the physical address of next stage node page or data page in n-ary tree, and data page is used for storage file data.
Preferably, data page and node page are dynamically distributes when to file write data.Specifically, write to file
During data, judging whether data page has existed according to writing address, if not existing, distributing data page, and this data of polishing
Page to required node page on path between root node, thus realizing random storage in amount of physical memory for the file data, and
Need not be by Documents Logical order in physical address space sequential storage.
Because the different files in a file system can be using different n-ary tree construction series, therefore each literary composition
The n-ary of this document data storage adopted n-ary tree construction series is identified in part corresponding file control information inode node
The tree content that stored of level digital section is different, can be 1,2,3 ... to wait different value.The n-ary tree being adopted based on different files
Structure series is different, the corresponding node page of the start physical address that the n-ary root vertex field in inode node preserves
nodepagenSeries also different.For example, using the file of 1-ary tree construction management, then the n-ary tree root section of inode node
The node page corresponding to start physical address that point field preserves is the 1st grade of node page nodepage of this document1;Using 2-
The file of ary tree construction management, then corresponding to the start physical address of n-ary root vertex field preservation of inode node
Node page is the 2nd grade of node page nodepage of this document2;Using the file of 3-ary tree construction management, then inode node
The node page corresponding to start physical address that n-ary root vertex field preserves is the 3rd level node page of this document
nodepage3;By that analogy, file is adopted highest several sections of point n-th grade of node page of page corresponding to n-ary tree construction
nodepagenCorresponding physical address is written to inode node n-ary root vertex field.
Preferably, the file in the file system of the present invention has logic length and physical length.Logic length represents this
If node is supplemented complete, the data volume that all data pages can store by the current n-ary tree of file.Physical length represents this article
The data volume sum of the page that all nodes of the current n-ary tree establishment of part occupy.Therefore, logic length is the length of file
Degree, physical length is then used for taking up room and remaining space of calculation document system.
3) with n-th grade of node page nodepage corresponding to filenPage number is root node, with (n-1) level node page
nodepagen-1Page number is the 1st grade of child node, by that analogy, with the 1st grade of node page nodepage1Page number is (n-1) level
Node, forms a n-ary tree and carries out storage management with all data to this document, the 1st grade of node page is data page.
Specifically, the amount of physical memory that file data is located, based on n-th grade of node page of the file corresponding to file
nodepagenPage number, (n-1) level node page nodepagen-1Page number ... ..., the 1st grade of node page nodepage1Page number, with
N level node page nodepagenPage number is root node, with (n-1) level node page nodepagen-1Page number is the 1st grade of child node,
By that analogy, the 1st grade of node page nodepage1Page number is (n-1) level child node, forms a n-ary tree and comes to number of files
Manage according to carrying out storage.In n-ary tree, every first nodes manage its child node, the number of every grade of child node in page table mode
It is fixed as 512.As shown in figure 3, the 1st grade of node page nodepage1Page is data page.That is, from root node to n-th -2
Level child node is used for organizing node page, and (n-1)th grade of child node is used for organizing data page.Root node stores the 1st grade of son
The physical address of node corresponding node page;1st grade of child node stores the physical address of the 2nd grade of child node corresponding node page;
By that analogy, (n-2) level child node stores the physical address of the corresponding node page of (n-1) level child node.1st grade of node page
For data page, all data pages occupy the afterbody node of n-ary tree.Therefore, in node page, the page physical address of storage can
Think next stage node page physical address or data page physical address.
Especially, when in the n-ary tree that file adopts, n is 1, the 1st grade of node page of this document only one of which.Corresponding n-
In ary tree, only one of which is with the 1st grade of node page nodepage1Page number is the root node of node, this nodepage1Page directly stores
Be file data, its essence is data page.
4) n-ary traversal of tree order is the logical order of data page.
Wherein, data page this data page of serial number when n-ary tree travels through logical page number (LPN) hereof.Therefore, may be used
To extrapolate the logical page number (LPN) of data page at this address place and this data page according to the logical address in file to root node
Path.
In the implementation method of the file system of the random access based on n-ary tree construction for the present invention, file system is created
When building file, comprise the following steps:
A) distribute an inode node;
The series n of the n-ary tree that b) specified file is adopted, is that file distributes one n-th grade node page nodepagen;
C) by n-th grade of node page nodepagenPhysical address write file corresponding inode node n-ary tree root
Node field;
D) the n-ary tree level numeral in the distributed inode node of the series n write of the n-ary tree that file is adopted
Section.
Illustrate the realization of the file system of the random access based on n-ary tree construction of the present invention by specific embodiment
Method.
If write operation order pressed by file 1, to the 1st logical page (LPAGE), the 500th logical page (LPAGE), the 600th logical page (LPAGE),
1000 logical page (LPAGE)s achieve write operation, then the n-ary tree construction of this document and file data distribution feelings in data field
Condition is as shown in Figure 4.This document has 3 node pages, 4 data pages, its interior joint page nodepage3Store section for root node
Point page nodepage21 and nodepage22 physical address, node page nodepage21 stores and respective logic page number pair
The data page datapage answering21 and data page datapage500Physical address, node page nodepage22 store and phase
Answer logical page number (LPN) corresponding data page datapage600And data page datapage1000Physical address.
Then, process will write the 700th logical page (LPAGE), and the logical page number (LPN) according to file calculates and understands, the 700th logical page (LPAGE) should
This belongs to second child node nodepage22 management, relative with the 700th logical page (LPAGE) based on page faults mechanism distribution one
The data page datapage answering700, finally by data page datapage700Physical address store node page nodepage22
Appropriate address field.
Then, process will write the 1300th logical page (LPAGE), and the logical page number (LPN) according to file calculates and understands, the 1300th logic
Page should belong to node page nodepage23 management, corresponding with the 1300th logical page (LPAGE) based on page faults mechanism distribution one
Data page datapage1300, and node page nodepage23.By data page datapage1300Physical address store section
Point page nodepage23 appropriate address field.Finally by node page nodepage23 physical address stores node page
nodepage3Appropriate address field.Fig. 5 and Fig. 6 respectively distribution feelings in data field for the file data page after write operation twice
The structure change figure of the n-ary tree of condition variation diagram and file.
Especially, in same file system, different files can have different series.Specifically, a literary composition
Multiple files are comprised, each file manages the be stored in physical address space of this document using n-ary tree construction in part system
Data.Series based on each file adopted n-ary tree construction is different, the data storage of achievable different capabilities rank.Example
As using the file of 1-ary tree construction management, its data storage maximum capacity is less than 4k;Using the management of 2-ary tree construction
File, its data storage maximum capacity is up to 2m;Using the file of 3-ary tree construction level page table structure management, its data storage
Maximum capacity is up to 1g.By the file of the management of the n-ary tree construction using bigger n, can achieve that more jumbo data is deposited
Storage.Therefore, a file system can achieve that the file of different capabilities rank stores, to meet the literary composition to different capabilities level demand
Part data storage.
Preferably, the series of the n-ary tree that file is adopted can dynamically increase.Specifically, file system is from number
Obtain an idle node page according to area as new root node;By root node new for the physical address write of file primitive root node
First position, and by the physical address of new root node and the series of n-ary tree that increases after 1 updates this document
In inode node.
Therefore, it is capable of being upgraded to (n+1) level by n level based on dynamic adjustment n-ary tree construction series, thus realizing literary composition
The upgrade expanding of part.The trigger event of increase series includes following several:
(1) address during data is write by posix mode and surmount current file logic length.
When address during data being write by posix mode surmounting current file logic length, it is adjusted to n+1 level from n level and moves
State adjustment n-ary tree construction series comprises the following steps:
One (n+1)th grade node page nodepage of distributionn+1As root node;
By n-th grade of node page nodepage corresponding to this documentnPhysical start address write newly assigned (n+1)
Level node page nodepagen+1Appropriate address field;
With (n+1) level node page nodepagen+1Start physical address update this document corresponding inode node
N-ary root vertex field;
Update the n-ary tree level digital section of this document corresponding inode node with (n+1);
Distribute a data page datapage based on page faults mechanism;
Polishing data page datapage to node page required on path between root node (datapage2,
Datapage3 ... ..., d atapagen).
(2) surmount current file logic length when current location being positioned by file pointer.
When surmounting current file logic length when current location is positioned by file pointer, it is adjusted to n+1 level from n level dynamic
Adjustment n-ary tree construction series comprises the following steps:
One (n+1)th grade node page nodepage of distributionn+1;
By n-th grade of node page nodepage corresponding to this documentnPhysical start address write newly assigned (n+1)
Level node page nodepagen+1Appropriate address field;
With (n+1) level node page nodepagen+1Start physical address update this document corresponding inode node
N-ary root vertex field;
Update the n-ary tree level digital section of this document corresponding inode node with (n+1).
(3) by mmap mode by File Mapping to process virtual space when the length specified surmounted current file logic
Length.
By mmap mode by File Mapping to process virtual space when the length specified to have surmounted current file logic long
When spending, it is adjusted to n+1 level and dynamically adjusts n-ary tree construction series comprise the following steps from n level:
One (n+1)th grade node page nodepage of distributionn+1;
By n-th grade of node page nodepage corresponding to this documentnPhysical start address write newly assigned (n+1)
Level node page nodepagen+1Appropriate address field;
With (n+1) level node page nodepagen+1Start physical address update this document corresponding inode node
N-ary root vertex field;
Update the n-ary tree level digital section of this document corresponding inode node with (n+1).
In sum, the implementation method of the file system of the random access based on n-ary tree construction of the present invention.So,
The present invention effectively overcomes various shortcoming of the prior art and has high industrial utilization.
Above-described embodiment only principle of the illustrative present invention and its effect, not for the restriction present invention.Any ripe
The personage knowing this technology all can carry out modifications and changes without prejudice under the spirit and the scope of the present invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete with institute under technological thought without departing from disclosed spirit such as
All equivalent modifications becoming or change, must be covered by the claim of the present invention.
Claims (9)
1. a kind of implementation method of the file system of the random access based on n-ary tree construction it is characterised in that: include
The all of file data of file system is managed in units of page;
Data area of inode area is set in file system, and described data field includes node page data page, described data page is used
In storage file data, described node page is used for storing the physical address of next stage node page or data page in n-ary tree;Described
The inode node being stored in inode area includes n-ary tree level digital section and n-ary root vertex field, described n-ary tree
Level digital section is used for the series of storage file adopted n-ary tree construction, and described n-ary root vertex field is used for storage file
The start physical address of n-th grade of node page;
N-th grade of node page page number corresponding to file as root node, with (n-1) level node page page number for the 1st grade of child node,
By that analogy, with the 1st grade of node page page number for (n-1) level child node, form a n-ary tree with all numbers to this document
Manage according to carrying out storage;Wherein the 1st grade node page is data page;
N-ary traversal of tree order is the logical order of data page.
2. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: described data page and described node page are in the mixing of described data field.
3. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: described data page and described node page are dynamically distributes when to file write data;During to file write data, root
Judge whether data page has existed according to writing address, if not existing, distributing data page, and this data page of polishing is to root node
Between node page required on path.
4. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: during file system establishment file, comprise the following steps:
One inode node of distribution;
The series n of the n-ary tree that specified file is adopted, is that file distributes n-th grade of node page;
The physical address of n-th grade of node page is write the n-ary root vertex field of file corresponding inode node;
The series n of the n-ary tree that file is adopted writes the n-ary tree level digital section in distributed inode node.
5. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: in same file system, different files can have the series of different n-ary trees.
6. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: the series of the n-ary tree that file is adopted can dynamically increase.
7. the implementation method of the file system of the random access based on n-ary tree construction according to claim 6, its feature
It is: dynamic the increased situation of series of the n-ary tree that triggering file is adopted includes:
Address during data is write by posix mode and surmounts current file logic length;
Current file logic length is surmounted when current location is positioned by file pointer;
By mmap mode by File Mapping to process virtual space when the length specified surmounted current file logic length.
8. the implementation method of the file system of the random access based on n-ary tree construction according to claim 6, its feature
It is: the series of the n-ary tree that file is adopted can dynamically increase and comprises the following steps:
File system obtains an idle node page as new root node from data field;
By first position of root node new for the physical address write of file primitive root node, and by new root node physically
The series of the n-ary tree behind location and increase by 1 updates in the inode node of this document.
9. the implementation method of the file system of the random access based on n-ary tree construction according to claim 1, its feature
It is: the size of described page is in the same size with operating system memory page.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611041427.1A CN106354890B (en) | 2016-11-22 | 2016-11-22 | A kind of implementation method of the file system of the random access based on N-ary tree construction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611041427.1A CN106354890B (en) | 2016-11-22 | 2016-11-22 | A kind of implementation method of the file system of the random access based on N-ary tree construction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106354890A true CN106354890A (en) | 2017-01-25 |
CN106354890B CN106354890B (en) | 2019-05-21 |
Family
ID=57862521
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611041427.1A Active CN106354890B (en) | 2016-11-22 | 2016-11-22 | A kind of implementation method of the file system of the random access based on N-ary tree construction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106354890B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180092A (en) * | 2017-05-15 | 2017-09-19 | 中国科学院上海微系统与信息技术研究所 | A kind of control method of file system, device and terminal |
CN108052541A (en) * | 2017-11-22 | 2018-05-18 | 中国科学院上海微系统与信息技术研究所 | The realization of file system based on multi-level page-table bibliographic structure, access method, terminal |
CN108334541A (en) * | 2017-12-18 | 2018-07-27 | 中兴通讯股份有限公司 | A kind of date storage method, device, equipment and storage medium |
CN108628753A (en) * | 2017-03-24 | 2018-10-09 | 华为技术有限公司 | Memory headroom management method and device |
CN109933564A (en) * | 2019-03-27 | 2019-06-25 | 中国科学院上海微系统与信息技术研究所 | File system management method, device, terminal, the medium of quick rollback are realized based on chained list and N-ary tree construction |
CN111512290A (en) * | 2017-12-27 | 2020-08-07 | 华为技术有限公司 | File page table management techniques |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103514291A (en) * | 2013-09-29 | 2014-01-15 | 西安交通大学 | Method for displaying tree structure data in text |
CN104537050A (en) * | 2014-12-25 | 2015-04-22 | 华中科技大学 | Method for batch and rapid establishment of metadata and data of file system |
WO2015090668A1 (en) * | 2013-12-17 | 2015-06-25 | Fujitsu Technology Solutions Intellectual Property Gmbh | Posix-compatible file system, method for producing a file list and memory apparatus |
US20160321295A1 (en) * | 2011-04-26 | 2016-11-03 | Zettaset, Inc. | Scalable Distributed Metadata File-System using Key-Value Stores |
-
2016
- 2016-11-22 CN CN201611041427.1A patent/CN106354890B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160321295A1 (en) * | 2011-04-26 | 2016-11-03 | Zettaset, Inc. | Scalable Distributed Metadata File-System using Key-Value Stores |
CN103514291A (en) * | 2013-09-29 | 2014-01-15 | 西安交通大学 | Method for displaying tree structure data in text |
WO2015090668A1 (en) * | 2013-12-17 | 2015-06-25 | Fujitsu Technology Solutions Intellectual Property Gmbh | Posix-compatible file system, method for producing a file list and memory apparatus |
CN104537050A (en) * | 2014-12-25 | 2015-04-22 | 华中科技大学 | Method for batch and rapid establishment of metadata and data of file system |
Non-Patent Citations (2)
Title |
---|
SHENG DING,ZHITANG SONG,HOUPENG CHEN,DAOLIN CAI,XIAOGANG CHEN: "The enhancement of write throughout for phase change memory", 《2010 10TH IEEE INTERNATIONAL CONFERENCE ON SOLID-STATE AND INTEGRATED CIRCUIT TECHNOLOGY》 * |
顾喜梅: "文件系统及磁盘管理实现机制深入研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108628753A (en) * | 2017-03-24 | 2018-10-09 | 华为技术有限公司 | Memory headroom management method and device |
CN108628753B (en) * | 2017-03-24 | 2021-02-23 | 华为技术有限公司 | Memory space management method and device |
CN107180092A (en) * | 2017-05-15 | 2017-09-19 | 中国科学院上海微系统与信息技术研究所 | A kind of control method of file system, device and terminal |
CN107180092B (en) * | 2017-05-15 | 2020-10-23 | 中国科学院上海微系统与信息技术研究所 | File system control method and device and terminal |
CN108052541A (en) * | 2017-11-22 | 2018-05-18 | 中国科学院上海微系统与信息技术研究所 | The realization of file system based on multi-level page-table bibliographic structure, access method, terminal |
CN108052541B (en) * | 2017-11-22 | 2021-07-27 | 中国科学院上海微系统与信息技术研究所 | File system implementation and access method based on multi-level page table directory structure and terminal |
CN108334541A (en) * | 2017-12-18 | 2018-07-27 | 中兴通讯股份有限公司 | A kind of date storage method, device, equipment and storage medium |
CN111512290A (en) * | 2017-12-27 | 2020-08-07 | 华为技术有限公司 | File page table management techniques |
CN111512290B (en) * | 2017-12-27 | 2023-09-22 | 华为技术有限公司 | File page table management technique |
CN109933564A (en) * | 2019-03-27 | 2019-06-25 | 中国科学院上海微系统与信息技术研究所 | File system management method, device, terminal, the medium of quick rollback are realized based on chained list and N-ary tree construction |
Also Published As
Publication number | Publication date |
---|---|
CN106354890B (en) | 2019-05-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106354890A (en) | Implementation method of random access file system based on N-ary tree structure | |
CN104899156B (en) | A kind of diagram data storage and querying method towards extensive social networks | |
CN102364474B (en) | Metadata storage system for cluster file system and metadata management method | |
CN107463447B (en) | B + tree management method based on remote direct nonvolatile memory access | |
CN102985909B (en) | Object for good lattice provides the method and apparatus of the high scalability network storage | |
CN105843748B (en) | The processing method and processing device of page in a kind of pair of memory | |
CN107180092B (en) | File system control method and device and terminal | |
CN108009008A (en) | Data processing method and system, electronic equipment | |
CN104331478B (en) | Data consistency management method for self-compaction storage system | |
CN103218312B (en) | file access method and system | |
CN103838853B (en) | Mixed file system based on different storage media | |
CN104298681B (en) | A kind of date storage method and device | |
US9250812B2 (en) | Leveraging a hybrid infrastructure for dynamic memory allocation and persistent file storage | |
CN103678172A (en) | Local data cache management method and device | |
CN107784121A (en) | Lowercase optimization method of log file system based on nonvolatile memory | |
CN108052541A (en) | The realization of file system based on multi-level page-table bibliographic structure, access method, terminal | |
CN104317742A (en) | Thin provisioning method for optimizing space management | |
CN102200892B (en) | Capacity expansion method based on dynamic redundant array of independent disks (RAID) system | |
CN106990915A (en) | A kind of SRM method based on storage media types and weighting quota | |
CN103885887B (en) | User data storage method, read method and system | |
CN109710175A (en) | Device and method for data storage management | |
CN103488685B (en) | Fragmented-file storage method based on distributed storage system | |
CN110188108A (en) | Date storage method, device, system, computer equipment and storage medium | |
CN105389367A (en) | Power network graphic multi-tense and multi-level distributed storage method based on Mongo database | |
CN103218305B (en) | The distribution method of memory space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |