CN110096234A - The method and its system of write performance in a kind of raising solid state hard disk - Google Patents
The method and its system of write performance in a kind of raising solid state hard disk Download PDFInfo
- Publication number
- CN110096234A CN110096234A CN201910358519.XA CN201910358519A CN110096234A CN 110096234 A CN110096234 A CN 110096234A CN 201910358519 A CN201910358519 A CN 201910358519A CN 110096234 A CN110096234 A CN 110096234A
- Authority
- CN
- China
- Prior art keywords
- lba
- red
- comp
- black
- node
- 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0866—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches for peripheral storage systems, e.g. disk cache
- G06F12/0871—Allocation or management of cache space
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06F3/0629—Configuration or reconfiguration of storage systems
- G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to the methods and its system of write performance in a kind of raising solid state hard disk；Wherein, method, comprising: S1 constructs red-black tree construction；S2, using root node as node LBA_comp to be compared；S3, judges whether LBA_x is less than LBA_comp；S4, LBA_x < LBA_comp；S5 judges that LBA_x is greater than and is also equal to LBA_comp；S6, LBA_x > LBA_comp, and LBA_comp does not have right child then and terminates to traverse and be suspended to LBA_x as right child under LBA_comp；S7, LBA_x=LBA_comp then search success.The present invention is had lower time complexity (i.e. higher write performance) and will not occupy additional memory resource, significantly reduced time complexity, improve the write performance of solid state hard disk using red-black tree construction.
Description
Technical field
The present invention relates to solid-state storage write performance technical field, more specifically refer to the property write in a kind of raising solid state hard disk
The method and its system of energy.
Background technique
The data that host is initiated in solid state hard disk (SSD) are first buffered in data cache (DRAM), subsequent to write data
It needs to judge whether have existed in data cache, needs to cover legacy data if existing (hit data cache),
Otherwise continue to be buffered in data cache as new data；Data are after the cache way in data cache determines judgement
Continue the height whether data hit data cache efficiency；Current techniques are using hash cache way (hash
Cache), but hash mode is there are two disadvantage, first is that time complexity is too high, second is that having additional memory (memory)
It is wasted；Therefore, it is impossible to meet demand.
Summary of the invention
It is an object of the invention to overcome the deficiencies of existing technologies, a kind of method for improving write performance in solid state hard disk is provided
And its system.
To achieve the above object, the present invention is used in lower technical solution:
A kind of method of write performance in raising solid state hard disk, comprising the following steps:
S1 constructs red-black tree construction, and traverses to red black tree；
S2 compares the size of LBA_x and LBA_comp using root node as node LBA_comp to be compared；
S3, judges whether LBA_x is less than LBA_comp；If so, into S4；If it is not, then entering S5；
S4, LBA_x < LBA_comp, and LBA_comp does not have left child, then terminates traversal and using LBA_x as left child
It is suspended under LBA_comp, otherwise using the left child of LBA_comp as new LBA_comp, then returns to S2, that is, carry out next layer
Comparison；
S5 judges that LBA_x is greater than and is also equal to LBA_comp；If more than into S6；If being equal to, enter S7；
S6, LBA_x > LBA_comp, and LBA_comp does not have right child then and terminates to traverse and hang LBA_x as right child
To under LBA_comp, otherwise using the right child of LBA_comp as new LBA_comp, S2 is then returned, that is, carries out next layer
Compare；
S7, LBA_x=LBA_comp then search success.
Its further technical solution are as follows: in the S1, it is assumed that the size of data cache is 4MB, and host is initiated to SSD
The data of 4MB, corresponding LBA address field are [LBA0, LBA8191], and red-black tree construction is carried out in data cache and is established.
Its further technical solution are as follows: the step of red and black tree construction is established is as follows:
A1, LBA0 enter data cache, and since red black tree at this time is sky, so LBA0 is as root node, and LBA0 is
Black；
A2, LBA1 enter data cache, since LBA1 is greater than LBA0, so right child of the LBA1 as LBA0, and
LBA1 is red；
A3, LBA2 enter data cache, determine that right child of the LBA2 as LBA1, LBA2 are black, carry out to LBA1
Left-handed operations, LBA1 needs to become LBA1 into black as root node at this time, is at this time a red black tree；
A4 is operated as A3 referring to A2, LBA3-LBA8191 is inserted into existing red black tree, after being inserted into new LBA,
If violating the characteristic of red black tree, three kinds of operations of left or right rotation or discoloration are carried out to incomplete red black tree, it is final so that it becomes
Complete red and black tree construction.
Its further technical solution are as follows: the characteristic of the red and black tree construction includes: that the left subtree of arbitrary node is not empty, then left
The value of all nodes is respectively less than the value of its root node in subtree；The right subtree of arbitrary node is not empty, then all sections on right subtree
The value of point is all larger than the value of its root node；The left and right subtree of arbitrary node is also respectively red black tree；There is no the section that LBA is equal
Point.
Its further technical solution are as follows: the characteristic of the red and black tree construction further include: node is red or black；Root is black
Color, all leaves are all black；Each red node must there are two the child nodes of black；From any node to each of which leaf
All simple paths all include equal number of dark node.
The system of write performance in a kind of raising solid state hard disk, comprising: construction unit, comparing unit, the first judging unit, and
Second judgment unit；
The construction unit is traversed for constructing red-black tree construction, and to red black tree；
The comparing unit, for comparing LBA_x's and LBA_comp using root node as node LBA_comp to be compared
Size；
First judging unit, for judging whether LBA_x is less than LBA_comp；
The second judgment unit is also equal to LBA_comp for judging that LBA_x is greater than.
Its further technical solution are as follows: in the construction unit, it is assumed that the size of data cache is 4MB, and host is to SSD
The data of 4MB are initiated, corresponding LBA address field is [LBA0, LBA8191], and red-black tree construction is carried out in data cache and is built
It is vertical.
Its further technical solution are as follows: the characteristic of the red and black tree construction includes: that the left subtree of arbitrary node is not empty, then left
The value of all nodes is respectively less than the value of its root node in subtree；The right subtree of arbitrary node is not empty, then all sections on right subtree
The value of point is all larger than the value of its root node；The left and right subtree of arbitrary node is also respectively red black tree；There is no the section that LBA is equal
Point.
Its further technical solution are as follows: the characteristic of the red and black tree construction further include: node is red or black；Root is black
Color, all leaves are all black；Each red node must there are two the child nodes of black；From any node to each of which leaf
All simple paths all include equal number of dark node.
Compared with the prior art, the invention has the advantages that: using red-black tree construction, there is lower time complexity
(i.e. higher write performance) and additional memory resource will not be occupied, significantly reduce time complexity, improved solid
The write performance of state hard disk.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Detailed description of the invention
Fig. 1 is the schematic diagram of prior art hash caching；
Fig. 2 is a kind of method flow diagram for improving write performance in solid state hard disk of the present invention；
Fig. 3 is the application schematic diagram that red black tree is inserted into LBA1 in the present invention；
Fig. 4 is the application schematic diagram that red black tree is inserted into LBA2 in the present invention；
Fig. 5 is the application schematic diagram of red-black tree construction in the present invention；
Fig. 6 is a kind of system block diagram for improving write performance in solid state hard disk of the present invention.
Specific embodiment
In order to more fully understand technology contents of the invention, combined with specific embodiments below to technical solution of the present invention into
One step introduction and explanation, but not limited to this.
Such as Fig. 1 to specific embodiment shown in fig. 6, wherein as shown in Figure 1, the request of data that host is initiated every time is all right
The address, i.e. [LBA_x, LBA_y] one section of LBA (Logical Block Address) are answered, LBA_x is indicated between this section of LBA band
Initial address, LBA_y indicate the end address between this section of LBA band, and each LBA corresponds to the data of 512B；To guarantee that data are consistent
Property, the firmware of SSD needs to cache these addresses LBA, to judge whether the data of the subsequent initiation of host have hit data
Cache (DRAM) if hit needs the legacy data in DRAM to override, deposit if not hitting as new data
Enter data cache.
The cache way of data cache is hash caching technology in current firmware design, which, which needs to define, calculates
The algorithm of hash value (Key), it is that host initiates the corresponding address LBA of data, N that Key=LBA_x%N, LBA_x are used in this example
For the number of hash key, N=8 in this example calculates the corresponding hash value in the address LBA with hash algorithm, then the LBA
Location is buffered in the column of corresponding hash value and (understands data cache by matrix).Assuming that data cache size be 4MB, host to
SSD initiates the data of 4MB, and corresponding LBA address field is [LBA0, LBA8191], according to these addresses LBA of hash caching technology
In distribution such as Fig. 1 of data cache.Aft engine initiate the sequential write to LBA8191 again, firmware is judged using hash algorithm
Whether data cache is hit, and calculating hash value is Key=8191%8=7, and then traversal checks Key7 in data cache
Whether there is or not LBA8191 in corresponding column, firmware needs to inquire 1024 final determine and exists in data cache in this example
LBA8191；It can be seen that the time complexity of hash caching technology is bigger, theoretically O (cache size/N/LBA size)=O
The time spent in (4MB/8/512B)=O (1024), the bigger data cache of time complexity stores a LBA, is also bigger,
Performance is lower, in addition by figure it is found that hash key number N it is bigger, store the additional memory (memory) of N number of hash key
Also bigger, so N is not too large when realizing.
As shown in Figures 2 to 5, the invention discloses a kind of methods of write performance in raising solid state hard disk, including following step
It is rapid:
S1 constructs red-black tree construction, and traverses to red black tree；
S2 compares the size of LBA_x and LBA_comp using root node as node LBA_comp to be compared；
S3, judges whether LBA_x is less than LBA_comp；If so, into S4；If it is not, then entering S5；
S4, LBA_x < LBA_comp, and LBA_comp does not have left child, then terminates traversal and using LBA_x as left child
It is suspended under LBA_comp, otherwise using the left child of LBA_comp as new LBA_comp, then returns to S2, that is, carry out next layer
Comparison；
S5 judges that LBA_x is greater than and is also equal to LBA_comp；If more than into S6；If being equal to, enter S7；
S6, LBA_x > LBA_comp, and LBA_comp does not have right child then and terminates to traverse and hang LBA_x as right child
To under LBA_comp, otherwise using the right child of LBA_comp as new LBA_comp, S2 is then returned, that is, carries out next layer
Compare；
S7, LBA_x=LBA_comp then search success.
Wherein, in the S1, it is assumed that the size of data cache is 4MB, and host initiates the data of 4MB to SSD, corresponding
LBA address field is [LBA0, LBA8191], and red-black tree construction is carried out in data cache and is established.
Wherein, the step of red-black tree construction is established is as follows:
A1, LBA0 enter data cache, and since red black tree at this time is sky, so LBA0 is as root node, and LBA0 is
Black；Wherein, according to characteristic 6, LBA0 is necessary for black, and in Fig. 3 (a), black box indicates leaf node；
A2, LBA1 enter data cache, since LBA1 is greater than LBA0, so right child of the LBA1 as LBA0, and
LBA1 is red；Wherein, according to the characteristic of red black tree 2, LBA1 should as the right child of LBA0, if LBA1 is also black,
Obviously it is unsatisfactory for characteristic 8, so LBA1 is necessary for red, it (b) is a red black tree in Fig. 3 (b)；
A3, LBA2 enter data cache, determine that right child of the LBA2 as LBA1, LBA2 are black, carry out to LBA1
Left-handed operations, LBA1 needs to become LBA1 into black as root node at this time, is at this time a red black tree；Wherein, according to characteristic
1 and 2, it is first determined LBA2 should be as the right child of LBA1, and in order to meet characteristic 7, LBA2 is black, as in Fig. 4 (c.1),
The apparent state violates characteristic 8, so carrying out left-handed operations to LBA1 in next step, (c.2) left-handed rear state is shown in Fig. 4,
LBA1 is but that red violates characteristic 6 as root node at this time, at this time (c.3) is one so needing to become LBA1 into black
Red black tree；
A4 is operated as A3 referring to A2, LBA3-LBA8191 is inserted into existing red black tree, after being inserted into new LBA,
If violating the characteristic of red black tree, three kinds of operations of left or right rotation or discoloration are carried out to incomplete red black tree, it is final so that it becomes
Complete red and black tree construction；Wherein, it is operated as A3 referring to A2, LBA3-LBA8191 is inserted into existing red black tree,
Be inserted into after new LBA the characteristic that may violate a red black tree, only need at this time according to the step of A2 or A3 to incomplete red
Black tree carries out three kinds of operations of left or right rotation or discoloration, may finally become complete red black tree.
Wherein, the characteristic of the red-black tree construction includes: that the left subtree of 1, arbitrary node is not empty, then all sections on left subtree
The value of point is respectively less than the value of its root node；2, the right subtree of arbitrary node is not empty, then the value of all nodes is big on right subtree
In the value of its root node；3, the left and right subtree of arbitrary node is also respectively red black tree；4, the section equal without LBA (key assignments)
Point.
Further, the characteristic of the red-black tree construction further include: 5, node be red or black；6, root is black, institute
Leaf is all black；7, each red node must there are two child node (all paths from each leaf to root of black
On cannot be there are two continuous red node)；8, all simple paths from any node to each of which leaf all include identical
The dark node of number.
Wherein, after [LBA0, LBA8191] is stored in data cache, final red black tree is as shown in Figure 5；With
The upper inside operating process data cached for the building process and data cache of red black tree.By the theory of red black tree it is found that
The height of final red black tree is O (logM), and wherein M is the number of LBA in cache, i.e. 4MB/512B=8192, so in this example
The height of red black tree is 13, and new LBA_x storage requires to look up in data cache whether have existed into data cache
LBA_x, so needing to be traversed for red black tree；Wherein, due to the inherent characteristic of red-black tree construction, which is not exceeded at most
13 times, so the time complexity of the algorithm is O (logM), it is O (13) in this example, it is multiple with the time of prior art hash caching
Miscellaneous degree O (1024), which is compared, has absolute advantage, so also being had on write performance using the caching technology of red black tree absolute excellent
Gesture.
As shown in fig. 6, the invention discloses a kind of systems of write performance in raising solid state hard disk, comprising: construction unit 10,
Comparing unit 20, the first judging unit 30 and second judgment unit 40；
The construction unit 10, traverses for constructing red-black tree construction, and to red black tree；
The comparing unit 20, for comparing LBA_x and LBA_comp using root node as node LBA_comp to be compared
Size；
First judging unit 30, for judging whether LBA_x is less than LBA_comp；
The second judgment unit 40 is also equal to LBA_comp for judging that LBA_x is greater than.
Wherein, in the construction unit 10, it is assumed that the size of data cache is 4MB, and host initiates the number of 4MB to SSD
According to corresponding LBA address field is [LBA0, LBA8191], and red-black tree construction is carried out in data cache and is established.
Further, the characteristic of the red-black tree construction includes: that the left subtree of arbitrary node is not empty, then owns on left subtree
The value of node is respectively less than the value of its root node；The right subtree of arbitrary node is not empty, then the value of all nodes is big on right subtree
In the value of its root node；The left and right subtree of arbitrary node is also respectively red black tree；There is no the node that LBA is equal.
Further, the characteristic of the red-black tree construction further include: node is red or black；Root is black, is owned
Leaf is all black；Each red node must there are two the child nodes of black；It is all from any node to each of which leaf
Simple path all includes equal number of dark node.
The present invention proposes a kind of highly efficient, stable cache way, i.e., red-black tree construction, when new technology has lower
Between complexity (i.e. higher write performance) and additional memory resource will not be occupied, significantly reduce time complexity,
Improve write performance.
It is above-mentioned that technology contents of the invention are only further illustrated with embodiment, in order to which reader is easier to understand, but not
It represents embodiments of the present invention and is only limitted to this, any technology done according to the present invention extends or recreation, by of the invention
Protection.Protection scope of the present invention is subject to claims.
Claims (9)
1. a kind of method for improving write performance in solid state hard disk, which comprises the following steps:
S1 constructs red-black tree construction, and traverses to red black tree；
S2 compares the size of LBA_x and LBA_comp using root node as node LBA_comp to be compared；
S3, judges whether LBA_x is less than LBA_comp；If so, into S4；If it is not, then entering S5；
S4, LBA_x < LBA_comp, and LBA_comp does not have left child, then terminates to traverse and be suspended to LBA_x as left child
Under LBA_comp, otherwise using the left child of LBA_comp as new LBA_comp, S2 is then returned, that is, carries out next layer of ratio
Compared with；
S5 judges that LBA_x is greater than and is also equal to LBA_comp；If more than into S6；If being equal to, enter S7；
S6, LBA_x > LBA_comp, and LBA_comp does not have right child then and terminates to traverse and be suspended to LBA_x as right child
Under LBA_comp, otherwise using the right child of LBA_comp as new LBA_comp, S2 is then returned, that is, carries out next layer of ratio
Compared with；
S7, LBA_x=LBA_comp then search success.
2. a kind of method for improving write performance in solid state hard disk according to claim 1, which is characterized in that in the S1,
Assuming that the size of data cache be 4MB, host to SSD initiate 4MB data, corresponding LBA address field be [LBA0,
LBA8191], red-black tree construction is carried out in data cache to be established.
3. a kind of method for improving write performance in solid state hard disk according to claim 2, which is characterized in that the red black tree
The step of structure is established is as follows:
A1, LBA0 enter data cache, and since red black tree at this time is sky, so LBA0 is used as root node, and LBA0 is black；
A2, LBA1 enter data cache, since LBA1 is greater than LBA0, so right child of the LBA1 as LBA0, and LBA1 is
It is red；
A3, LBA2 enter data cache, determine that right child of the LBA2 as LBA1, LBA2 are black, carry out to LBA1 left-handed
Operation, LBA1 needs to become LBA1 into black as root node at this time, is at this time a red black tree；
A4 is operated as A3 referring to A2, LBA3-LBA8191 is inserted into existing red black tree, after being inserted into new LBA, if disobeying
The characteristic of anti-red black tree carries out three kinds of operations of left or right rotation or discoloration to incomplete red black tree, final so that it becomes complete
Red-black tree construction.
4. a kind of method for improving write performance in solid state hard disk according to claim 3, which is characterized in that the red black tree
The characteristic of structure includes: that the left subtree of arbitrary node is not empty, then the value of all nodes is respectively less than its root node on left subtree
Value；The right subtree of arbitrary node is not empty, then on right subtree the value of all nodes be all larger than it root node value；Arbitrary node
Left and right subtree is also respectively red black tree；There is no the node that LBA is equal.
5. a kind of method for improving write performance in solid state hard disk according to claim 4, which is characterized in that the red black tree
The characteristic of structure further include: node is red or black；Root is black, and all leaves are all black；Each red node is necessary
There are two the child nodes of black；All simple paths from any node to each of which leaf all include equal number of black section
Point.
6. a kind of system for improving write performance in solid state hard disk characterized by comprising construction unit, comparing unit, first sentences
Disconnected unit and second judgment unit；
The construction unit is traversed for constructing red-black tree construction, and to red black tree；
The comparing unit, for comparing the big of LBA_x and LBA_comp using root node as node LBA_comp to be compared
It is small；
First judging unit, for judging whether LBA_x is less than LBA_comp；
The second judgment unit is also equal to LBA_comp for judging that LBA_x is greater than.
7. a kind of system for improving write performance in solid state hard disk according to claim 6, which is characterized in that the building is single
In member, it is assumed that the size of data cache be 4MB, host to SSD initiate 4MB data, corresponding LBA address field be [LBA0,
LBA8191], red-black tree construction is carried out in data cache to be established.
8. a kind of system for improving write performance in solid state hard disk according to claim 7, which is characterized in that the red black tree
The characteristic of structure includes: that the left subtree of arbitrary node is not empty, then the value of all nodes is respectively less than its root node on left subtree
Value；The right subtree of arbitrary node is not empty, then on right subtree the value of all nodes be all larger than it root node value；Arbitrary node
Left and right subtree is also respectively red black tree；There is no the node that LBA is equal.
9. a kind of system for improving write performance in solid state hard disk according to claim 8, which is characterized in that the red black tree
The characteristic of structure further include: node is red or black；Root is black, and all leaves are all black；Each red node is necessary
There are two the child nodes of black；All simple paths from any node to each of which leaf all include equal number of black section
Point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358519.XA CN110096234A (en) | 2019-04-30 | 2019-04-30 | The method and its system of write performance in a kind of raising solid state hard disk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358519.XA CN110096234A (en) | 2019-04-30 | 2019-04-30 | The method and its system of write performance in a kind of raising solid state hard disk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110096234A true CN110096234A (en) | 2019-08-06 |
Family
ID=67446486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910358519.XA Pending CN110096234A (en) | 2019-04-30 | 2019-04-30 | The method and its system of write performance in a kind of raising solid state hard disk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084032A (en) * | 2020-09-15 | 2020-12-15 | 电子科技大学 | A Write-Optimized Persistent Memory Heap Management Method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140025708A1 (en) * | 2012-07-20 | 2014-01-23 | Jan Finis | Indexing hierarchical data |
| CN103902700A (en) * | 2014-04-01 | 2014-07-02 | 浙江大学 | Tree structure data processing method |
| US20140344530A1 (en) * | 2013-03-15 | 2014-11-20 | Sunil Sayyaparaju | Method and system of implementing a database index in shared memory |
| CN107844436A (en) * | 2017-11-02 | 2018-03-27 | 郑州云海信息技术有限公司 | The organization and management method of dirty data, system and storage system in a kind of caching |
| CN109684236A (en) * | 2018-12-25 | 2019-04-26 | 广东浪潮大数据研究有限公司 | A kind of data write buffer control method, device, electronic equipment and storage medium |
-
2019
- 2019-04-30 CN CN201910358519.XA patent/CN110096234A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140025708A1 (en) * | 2012-07-20 | 2014-01-23 | Jan Finis | Indexing hierarchical data |
| US20140344530A1 (en) * | 2013-03-15 | 2014-11-20 | Sunil Sayyaparaju | Method and system of implementing a database index in shared memory |
| CN103902700A (en) * | 2014-04-01 | 2014-07-02 | 浙江大学 | Tree structure data processing method |
| CN107844436A (en) * | 2017-11-02 | 2018-03-27 | 郑州云海信息技术有限公司 | The organization and management method of dirty data, system and storage system in a kind of caching |
| CN109684236A (en) * | 2018-12-25 | 2019-04-26 | 广东浪潮大数据研究有限公司 | A kind of data write buffer control method, device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 萧逸才: "红黑树-插入", 《CSDN,HTTPS://BLOG.CSDN.NET/XYC_CSDN/ARTICLE/DETAILS/80206819》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084032A (en) * | 2020-09-15 | 2020-12-15 | 电子科技大学 | A Write-Optimized Persistent Memory Heap Management Method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376123B (en) | Method for managing files, distributed storage system and management node | |
| CN110058822B (en) | Transverse expansion method for disk array | |
| WO2020010502A1 (en) | Distributed data redundant storage method based on consistent hash algorithm | |
| US8208408B2 (en) | Tree-based node insertion method and memory device | |
| CN109284299B (en) | Method for reconstructing a hybrid index with storage awareness | |
| CN109800185B (en) | Data caching method in data storage system | |
| CN105573682B (en) | A kind of SAN storage system and its data read-write method | |
| CN107391034A (en) | A kind of duplicate data detection method based on local optimization | |
| KR102437775B1 (en) | Page cache device and method for efficient mapping | |
| CN107704212B (en) | A data processing method and device | |
| US20160294693A1 (en) | Routing Lookup Method and Device, and Construction Method for B-tree Structure | |
| CN106569963A (en) | Buffering method and buffering device | |
| CN110750957B (en) | Cache system verification method of high-efficiency multi-core RISC-V processor | |
| CN102023810A (en) | Method and device for writing data and redundant array of inexpensive disk | |
| CN113032390B (en) | Workload self-adaptive learning type indexing method in memory database | |
| CN105550246B (en) | The system and method for load networks picture under Android platform | |
| CN102006297B (en) | Two-level policy decision-based access control method and system | |
| RU2525752C2 (en) | Method and apparatus for storing, reading and writing compound document | |
| CN107844436B (en) | A method, system and storage system for organizing and managing dirty data in cache | |
| CN104573571B (en) | A kind of generation method of smart card security file system | |
| CN107329836B (en) | Multi-system memory management method and device and mobile terminal | |
| CN110058964A (en) | Data reconstruction method, data recovery system and computer program product | |
| CN110096234A (en) | The method and its system of write performance in a kind of raising solid state hard disk | |
| CN102662855A (en) | Storage method and system of binary tree | |
| CN120233958B (en) | Data read-write request processing method, electronic device, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |