CN105892938A - Optimization method and system of disk cache system - Google Patents
Optimization method and system of disk cache system Download PDFInfo
- Publication number
- CN105892938A CN105892938A CN201610184620.4A CN201610184620A CN105892938A CN 105892938 A CN105892938 A CN 105892938A CN 201610184620 A CN201610184620 A CN 201610184620A CN 105892938 A CN105892938 A CN 105892938A
- Authority
- CN
- China
- Prior art keywords
- file
- disk
- hard disk
- mechanical hard
- files
- 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
- 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; 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
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/068—Hybrid storage 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)
Abstract
The invention provides an optimization method of a disk cache system. The optimization method comprises the following steps: determining a historical access frequency of each file of a first mechanical hard disk of the disk cache system; determining the files, the historical access frequencies of which exceed a predetermined threshold value, as hot files; continuously writing all the files in the first mechanical hard disk in a second mechanical hard disk, wherein relative to the residual files except the hot files in all the files, file data of the hot files is preferentially written in the second mechanical hard disk from a disk outer channel to a disk inner channel; generating a disk mirror image on the basis of the file data in the second mechanical hard disk in which all the files are continuously written; covering the files in the first mechanical hard disk by utilizing the disk mirror image. Embodiments of the invention furthermore provide a streaming media file distribution system. According to the optimization method the fragment arrangement of the files of the disk cache system is realized, and the hot files and cold files are stored separately, so that the response speed of the hot files in the disk cache system is enhanced.
Description
Technical field
The present embodiments relate to computer memory technical field, particularly relate to a kind of disk buffering system
Optimization method and system.
Background technology
Along with developing rapidly of computer technology, modern society comes into cybertimes, and computer
Being exactly carrier and the instrument of network, people calculate the requirement of speed and function increasingly for computer
Height, in order to meet these requirements, computer not only to improve usefulness, hardware store from software product
Aspect also to make corresponding improvement, in order to adapts to more and more diversified functional requirement.
Computer, during running, can produce some disk fragmentses, the disk fragments meeting of time length
Cause poor system performance, such as run program, browse webpage, storage file time slow.
Disk fragments is analyzed and arranges accordingly, it is desirable to utilize disk to arrange software, to keep magnetic
Dish file is relative to the seriality of memory space.Prior art is come frequently with disk fragments finishing tool
Fragment is arranged, the defragmentation instrument carried such as Windows operating system, or other the 3rd
The disk fragments finishing tool of side;And the method that traditional disk fragments finishing tool puts chips of the magnetic disc in order
It is by file fragmentation from the memory space that its former storage position is transported to the free time, by scattered fragment weight
Newly arrange back in a continuous manner on former memory space, thus form continuous on memory space of file
Preserve.
In above-mentioned prior art, there are the following problems in the arrangement of disk fragments:
Firstly, since be little to carry out accessing operation during disk fragments arranges, for surplus
When residual magnetism disk space is too small, or there is the file of heavy fragmentation, finishing time is very long and arranges effect
The most very poor, even owing to there is not enough idle storage space, and it cannot be carried out fragment at all
Arrange;Furthermore, according to user, disk file can be divided into frequent operation by the access frequency of disk file
Focus file and operation cold spot file infrequently, by disk method for sorting of the prior art without
Method realizes focus file and the partitioned storage of cold spot file, and focus file is to compare to meet disk use
The operating habit at family, therefore when multiple focus files are read out by disk user, due to focus literary composition
The discontinuity of part memory space, increases the tracking time, has had a strong impact on the user's body that disk reads
Test.
Summary of the invention
The embodiment of the present invention provides optimization method and the system of a kind of disk buffering system, above-mentioned in order to solve
At least one technical problem illustrated in prior art.
On the one hand, the embodiment of the present invention provides the optimization method of a kind of disk buffering system, including:
Determine the history visitation frequency of each file in the first mechanical hard disk in described disk buffering system;
The file that history visitation frequency exceedes predetermined threshold is defined as focus file;
All Files in first mechanical hard disk is continuously written into the second mechanical hard disk, wherein, relative to institute
For having in file the residue file in addition to described focus file, the file data of described focus file from
Disk outer course road in disk preferentially writes described second mechanical hard disk;
Based on the file data in described described second mechanical hard disk being continuously written into All Files, generate magnetic
Disk mirroring;
Described disk mirroring is utilized to cover the file in described first mechanical hard disk.
On the other hand, the embodiment of the present invention also provides for a kind of optimization system for disk buffering system, its
Include:
History visitation frequency determines unit, for determining the first mechanical hard disk in described disk buffering system
In the history visitation frequency of each file;
Focus document determining unit, is defined as heat for history visitation frequency exceedes the file of predetermined threshold
Dot file;
Write control unit is hard for the All Files in the first mechanical hard disk is continuously written into the second machinery
Dish, wherein, for residue file in addition to described focus file in All Files, described heat
The file data of dot file preferentially writes described second mechanical hard disk from disk outer course road in disk;
Mirror image signal generating unit, for based in described described second mechanical hard disk being continuously written into All Files
File data, generate disk mirroring;
Data convert unit, for utilizing described disk mirroring to cover the file in described first mechanical hard disk.
The optimization method of the disk buffering system provided by the embodiment of the present invention and system, it is achieved that to magnetic
Focus file in the defragmentation of dish caching system, and the disk buffering system after achieving arrangement exists
Coutinuous store on mechanical hard disk, improves the performance of read-write focus file, compared to prior art;This
Inventive embodiments has the advantages that
First, by mechanical hard disk to be arranged in disk buffering system is continuously written into another mechanical hard disk,
Then the disk mirroring that another mechanical hard disk is generated covers the file of mechanical hard disk to be arranged, and it is right to complete
The defragmentation of mechanical hard disk to be arranged so that comprise the institute of focus file in mechanical hard disk to be arranged
There is file to achieve the seriality of storage, improve the service processing performance of disk buffering system;Furthermore,
Focus file usually compares the operating habit of the person that meets disk access, due to the 0 of common mechanical hard disk
Magnetic track is on outer course, and magnetic head then starts to seek search file from 0 magnetic track, is implemented by the present invention
The focus of the operating habit of what example made main storage on the disk outer course after arranging the is person that meets disk access
File, it is achieved that when disk access person accesses focus file again, can reduce the time that tracking is consumed,
And improve service response speed to optimize Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that under,
Accompanying drawing during face describes is some embodiments of the present invention, for those of ordinary skill in the art,
On the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is illustrated that the flow chart of the optimization method of the disk buffering system of one embodiment of the invention;
Fig. 2 is illustrated that the structural representation of the optimization system of the disk buffering system of one embodiment of the invention
Figure.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
See the flow process of optimization method that Fig. 1 is illustrated that the disk buffering system of one embodiment of the invention
Figure, including:
S11: determine that the history of each file in the first mechanical hard disk in described disk buffering system accesses frequency
Secondary;
S12: the file that history visitation frequency exceedes predetermined threshold is defined as focus file;
S13: the All Files in the first mechanical hard disk is continuously written into the second mechanical hard disk, wherein, relatively
In All Files for residue file in addition to described focus file, the number of files of described focus file
Described second mechanical hard disk is preferentially write according to from disk outer course road in disk;
S14: based on the file data in described described second mechanical hard disk being continuously written into All Files is raw
Become disk mirroring;
S15: utilize described disk mirroring to cover the file in described first mechanical hard disk.
By the optimization method of the disk buffering system that the embodiment of the present invention provides, it is achieved that to disk buffering
Focus file in the defragmentation of system, and the disk buffering system after achieving arrangement is hard at machinery
Coutinuous store on dish, improves the performance of read-write focus file;Compared to prior art, the present invention is real
Execute example method to have the advantages that
First, by mechanical hard disk to be arranged in disk buffering system is continuously written into another mechanical hard disk,
Then the disk mirroring that another mechanical hard disk is generated covers the file of mechanical hard disk to be arranged, and it is right to complete
The defragmentation of mechanical hard disk to be arranged so that comprise the institute of focus file in mechanical hard disk to be arranged
File is had to achieve the seriality of storage, compared to prior art carries out in a mechanical hard disk fragment
Arrange, it is to avoid data are moved between memory block frequently when defragmentation, improve disk buffering
Service processing performance after the optimized process of system;Furthermore, focus file usually compares and meets disk visit
The operating habit of the person of asking, owing to 0 magnetic track of common mechanical hard disk is on outer course, magnetic head is then from 0
Magnetic track starts to seek search file, makes on the disk outer course after arranging main by the embodiment of the present invention
Storage is the focus file of operating habit of the person that meets disk access, it is achieved that when disk access person again
When accessing focus file, the time that tracking is consumed can be reduced, and improve service response speed to optimize use
Family is experienced.
As a kind of preferred embodiment of embodiment of the present invention method, disk buffering system also includes that solid-state is hard
Dish, after the All Files in the first mechanical hard disk is continuously written into the second mechanical hard disk, also includes: will
File metadata write solid state hard disc in described All Files.
Should explain be solid state hard disc in embodiment of the present invention method and mechanical hard disk to be arranged is relevant
Connection, i.e. when acquiring about in time arranging the access request of mechanical hard disk, preferentially inquire about above-mentioned solid-state
Hard disk;It addition, metadata is the data describing data, the information of data attribute is mainly described, or
It is used for supporting such as to indicate the functions such as storage position, historical data, resource lookup, file record;It addition,
Metadata is also a kind of electronic type catalogue, and in order to reach the purpose of scheduling, metadata allows for retouching
State the interior perhaps characteristic of data, and then the purpose assisting data retrieval can be reached by metadata.
Solid state hard disc is solid-state storage, belongs to Flash memory, and service life is long, it is not easy to damage,
And have more faster read or write speed than mechanical hard disk, install solid-state the most in a computer additional
Hard disk, as system disk, enters system time ratio common fast more than 20%;In embodiment of the present invention side
In method, by the file metadata of the disk file of mechanical hard disk to be arranged is write solid state hard disc, it is achieved
When receiving the access request corresponding to mechanical hard disk, it is possible to by inquiry solid state hard disc is deposited
The file metadata of storage obtains the data file being positioned in mechanical hard disk corresponding to described access request.
As a kind of preferred embodiment of embodiment of the present invention method, by the file unit number in All Files
After write solid state hard disc, also include: will write solid less than the focus file of solid state hard disc residual capacity
State hard disk.
Owing to focus file is the file comparing and meeting disk system visitor's operating habit, generally can be pre-
Survey disk system visitor and access the probability of focus file when next time accesses disk buffering system relative to it
His file also can be some larger;By embodiment of the present invention method, focus file backup is write solid state hard disc,
Achieve the quick response for access request of the focus file.
As a kind of preferred embodiment of embodiment of the present invention method, the writing mode of described focus file is
Write the most successively according to the history visitation frequency of focus file.
As further optimizing, according to the sequence of history visitation frequency of focus file successively to heat
Dot file is ranked up, and generates corresponding focus document queue;According to above-mentioned focus document queue successively
Focus file is write.
Should explain, the write of the focus file in embodiment of the present invention method process not only comprise by
Focus file in mechanical hard disk to be arranged writes backup mechanical hard disk successively, also comprises hard for backup machinery
Focus file in dish writes solid state hard disc successively, also comprises the focus file in mechanical hard disk to be arranged
Write solid state hard disc successively.
Although solid state hard disc has good readwrite performance, but price general charged is more expensive and memory capacity is less,
Therefore when the file data in disk buffering system is huger when, by standby for all of file metadata
Part to after solid state hard disc, generally cannot realize focus file is backed up to solid state hard disc the most completely;
On the one hand, by embodiment of the present invention method, it is achieved that preferentially by focus file relative to other focuses
The focus file that the temperature of file is higher writes solid state hard disc, ensures disk buffering system to current temperature relatively
The quick response of high focus file;On the other hand, general due to the file temperature in disk buffering system
In the case of can be continually changing, by we embodiment method, the focus in solid state hard disc can be updated
File, it is ensured that necessarily comprise the focus file that current temperature is the highest in the focus file in solid state hard disc.
As a kind of preferred embodiment of embodiment of the present invention method, determine first in disk buffering system
The history visitation frequency of each file in mechanical hard disk includes: periodically detect in the first mechanical hard disk
Each file plays the history visitation frequency in set time section forward when Autonomous test.
More specifically, can determine by periodically inquiring about the access log file of the first mechanical disk
The be accessed for history of each file in first mechanical hard disk in during relatively going up the interval inquiry once inquired about
Visitation frequency.
By embodiment of the present invention method, it is achieved that All Files in regular update arrangement to be optimized disk
File temperature, and redefine the focus file in arrangement disk to be optimized.
As a kind of preferred embodiment of embodiment of the present invention method, it is associated with above-mentioned second mechanical hard disk
The quantity of mechanical hard disk be multiple, cover in described first mechanical hard disk utilizing described disk mirroring
Also include after file:
Empty all of file data in described second mechanical hard disk;
To other in addition to described second mechanical hard disk and the first mechanical hard disk in described disk buffering system
Mechanical hard disk is repeated in performing above-mentioned optimization and collation step.
As further optimizing, between the multiple disks to be arranged in disk buffering system, there is one
The priority of precedence is processed about optimization.
By embodiment of the present invention method, a backup mechanical hard disk is utilized to complete disk buffering system
In the optimization of multiple mechanical hard disks to be arranged process.
In a kind of specific embodiment of the present invention, disk buffering system includes the first of arrangement to be optimized
Mechanical hard disk, about as follows to the specific implementation method of the first mechanical hard disk optimization and collation:
Disk buffering system judges when present system time is the optimization and collation time, then to utilize another blank diskette
As the second mechanical hard disk, the first mechanical hard disk is performed optimization and collation step, including:
Inquire about access log file in the first mechanical hard disk to determine going through of each file in the first mechanical hard disk
History visitation frequency;
The file that history visitation frequency exceedes predetermined threshold is defined as focus file;
Obtain the focus file storage address of all focus files in the first mechanical hard disk, and according to above-mentioned heat
Dot file storage address by all focus files in the first mechanical hard disk from disk outer course to disk Nei Daolian
Continue into the second mechanical hard disk;
After all focus files in the first mechanical hard disk all write the second mechanical hard disk, obtain heat extraction point
The ordinary file storage address of the ordinary file outside file, and depend on according to above-mentioned ordinary file storage address
Secondary ordinary file is continuously written into the second mechanical hard disk.
After the All Files in the first mechanical hard disk all writes the second mechanical hard disk, then based on above-mentioned continuously
File data in described second mechanical hard disk of write All Files, generates disk mirroring;
Above-mentioned disk mirroring is write the first mechanical hard disk in the way of mirror image copies into, completes the first machinery
Hard disk stores the replacement of file.
Further, the file metadata in the second mechanical hard disk is backed up to relevant to the second mechanical hard disk
On the solid state hard disc of connection, when there is the access request to the second mechanical hard disk, the above-mentioned solid-state of preferential access
Hard disk.
Further, hard by writing described solid-state less than the focus file of described solid state hard disc residual capacity
Dish.
As one optimization, this specific embodiment there is also the temperature of focus file and evaluates mechanism, the most logical
The visitation frequency of heat spot file carries out temperature sequence to focus file, therefore in above-mentioned focus file write the
The mode of two mechanical hard disks and/or solid state hard disc can be preferentially to write according to the focus file that temperature is high
Mode performs.Thus being not difficult to find out, embodiment of the present invention method is not required for all of focus file all
Solid state hard disc can be backed up to, but can realize hard for some focus files write solid-state the highest for hot value
Dish.
Further, after above-mentioned first mechanical hard disk has been performed optimization and collation, continue disk is delayed
Other mechanical hard disks to be arranged in deposit system repeat above optimization and collation step.
About the one side of specific embodiment of the invention method application, can be to apply in Virtual network operator institute
On the server disposed, the server accessed request frequency should be chosen to be about the above-mentioned optimization and collation time
The relatively low period, such as, selecting at 2 o'clock to 4 o'clock of morning in every day, i.e. disk buffering system every day is early
Upper 2 start to perform optimization and collation work;Point every morning 2 is achieved by the specific embodiment of the invention
Again focus file will be determined, and then update the focus file on disk outer course and mechanical hard disk,
Achieve the service processing ability of focus file in the server that Internet service provider is disposed, the most real
Show the metadata backed up on regular update solid state hard disc;Further relate to the judgement of above-mentioned predetermined threshold
Be referred to server every day file the average access frequency and determine, such as: a Website server
Daily average every day be accessed 1,000,000 times, and server has 100 data files, the most permissible
Predetermined threshold is defined as average every day 10,000 times, surpasses when the access times on the same day of a certain file further
Cross 10,000 times, then may determine that this document is focus file.
See Fig. 2 and be illustrated that a kind of disk buffering of one embodiment of the invention optimizes the structural representation of system
Figure, including:
History visitation frequency determines unit, for determining the first mechanical hard disk in described disk buffering system
In the history visitation frequency of each file;
Focus document determining unit, is defined as heat for history visitation frequency exceedes the file of predetermined threshold
Dot file;
Write control unit is hard for the All Files in the first mechanical hard disk is continuously written into the second machinery
Dish, wherein, for residue file in addition to described focus file in All Files, described heat
The file data of dot file preferentially writes described second mechanical hard disk from disk outer course road in disk;
Mirror image signal generating unit, for based in described described second mechanical hard disk being continuously written into All Files
File data, generate disk mirroring;
Data convert unit, for utilizing described disk mirroring to cover the file in described first mechanical hard disk.
By the optimization system of the disk buffering system that the embodiment of the present invention provides, it is achieved that to disk buffering
Focus file in the defragmentation of system, and the disk buffering system after achieving arrangement is hard at machinery
Coutinuous store on dish, improves the performance of read-write focus file, compared to prior art;The present invention is real
Execute example to have the advantages that
First, by mechanical hard disk to be arranged in disk buffering system is continuously written into another mechanical hard disk,
Then the disk mirroring that another mechanical hard disk is generated covers the file of mechanical hard disk to be arranged, and it is right to complete
The defragmentation of mechanical hard disk to be arranged so that comprise the institute of focus file in mechanical hard disk to be arranged
There is file to achieve the seriality of storage, improve the service processing performance of disk buffering system;Furthermore,
Focus file usually compares the operating habit of the person that meets disk access, due to the 0 of common mechanical hard disk
Magnetic track is on outer course, and magnetic head then starts to seek search file from 0 magnetic track, is implemented by the present invention
The focus of the operating habit of what example made main storage on the disk outer course after arranging the is person that meets disk access
File, it is achieved that when disk access person accesses focus file again, can reduce the time that tracking is consumed,
And improve service response speed to optimize Consumer's Experience.
As a kind of preferred embodiment of embodiment of the present invention system, described disk buffering system also includes solid
State hard disk, it is characterised in that said write control unit also includes:
Metadata writing module, for writing solid state hard disc by the file metadata in described All Files.
Should explain be solid state hard disc in embodiment of the present invention system and mechanical hard disk to be arranged is relevant
Connection, i.e. when acquiring about in time arranging the access request of mechanical hard disk, preferentially inquire about above-mentioned solid-state
Hard disk.
Solid state hard disc is solid-state storage, belongs to Flash memory, and service life is long, it is not easy to damage,
And have more faster read or write speed than mechanical hard disk, the most often install SSD solid state hard disc additional and make
For system disk, enter system time ratio common fast more than 20%;In embodiment of the present invention system,
By the file metadata of the disk file of mechanical hard disk to be arranged is write solid state hard disc, it is achieved that connecing
When receiving the access request corresponding to mechanical hard disk, it is possible to by the literary composition stored in inquiry solid state hard disc
Part metadata obtains the data file being positioned in mechanical hard disk corresponding to described access request.
As a kind of preferred embodiment of embodiment of the present invention system, said write control unit also includes:
The focus file writing module being connected with described metadata writing module, being used for will be less than described solid-state
The focus file of hard disk remaining capacity writes described solid state hard disc.
Owing to focus file is the file comparing and meeting disk system visitor's operating habit, generally can be pre-
Survey disk system visitor and access the probability of focus file when next time accesses disk buffering system relative to it
His file also can be some larger;By embodiment of the present invention system, focus file backup is write solid state hard disc,
Achieve the quick response for access request of the focus file.
As a kind of preferred embodiment of embodiment of the present invention system, said write control unit also includes:
Focus document input module, being used for the writing mode of focus file is to access according to the history of focus file
The frequency writes the most successively.
As further optimizing, above-mentioned write control unit also includes focus queue module, for according to
Focus file is ranked up by the sequence of the history visitation frequency of focus file successively, and generates corresponding
Focus document queue with successively by focus file write.
Should explain, the write of the focus file in embodiment of the present invention system process not only comprise by
Focus file in mechanical hard disk to be arranged writes backup mechanical hard disk successively, also comprises hard for backup machinery
Focus file in dish writes solid state hard disc successively, also comprises the focus file in mechanical hard disk to be arranged
Write solid state hard disc successively.
Although solid state hard disc has good readwrite performance, but price general charged is more expensive and memory capacity is less,
Therefore when the file data in disk buffering system is huger when, by standby for all of file metadata
Part to after solid state hard disc, generally cannot realize focus file is backed up to solid state hard disc the most completely;
On the one hand, by embodiment of the present invention system, it is achieved that preferentially by focus file relative to other focuses
The focus file that the temperature of file is higher writes solid state hard disc, ensures disk buffering system to current temperature relatively
The quick response of high focus file;On the other hand, general due to the file temperature in disk buffering system
In the case of can be continually changing, by we embodiment system, the focus in solid state hard disc can be updated
File, it is ensured that necessarily comprise the focus file that current temperature is the highest in the focus file in solid state hard disc.
As a kind of preferred embodiment of embodiment of the present invention system, described history visitation frequency determines unit
For periodically detect each file in described first mechanical hard disk rise when Autonomous test fix forward time
Between history visitation frequency in section.
By embodiment of the present invention system, it is achieved that All Files in regular update arrangement to be optimized disk
File temperature, and redefine the focus file in arrangement disk to be optimized.
As a kind of preferred embodiment of embodiment of the present invention system, it is associated with above-mentioned second mechanical hard disk
The quantity of mechanical hard disk be multiple, also include repeated optimization unit with described data convert unit is connected,
For after completing described first mechanical hard disk to perform optimization and collation step, to described disk buffering system
In other mechanical hard disks be repeated in performing above-mentioned optimization and collation step.
As further optimizing, described repeated optimization unit also includes prioritization module, for really
Between multiple disks to be arranged in fixed above-mentioned disk buffering system about processing the preferential of precedence
Level.
By embodiment of the present invention system, a backup mechanical hard disk is utilized to complete disk buffering system
In the optimization of multiple mechanical hard disks to be arranged process.
The embodiment of the present invention can realize related function module and unit by hardware processor.
In the application on the one hand of embodiment of the present invention system, embodiment of the present invention system can be built at clothes
In business device, especially build on streaming media server, when the embodiment of the present invention is applied in streaming media service
Time on device, can greatly optimize the response speed of current hotspot files in stream media, optimize most of visitor
The Consumer's Experience of family colony.
Device embodiment described above is only schematically, the list wherein illustrated as separating component
Unit can be or may not be physically separate, and the parts shown as unit can be or also
Can not be physical location, i.e. may be located at a place, or multiple NE can also be distributed to
On.Some or all of module therein can be selected according to the actual needs to realize the present embodiment scheme
Purpose.Those of ordinary skill in the art, in the case of not paying performing creative labour, are i.e. appreciated that
And implement.
Through the above description of the embodiments, those skilled in the art is it can be understood that arrive each reality
The mode of executing can add the mode of required general hardware platform by software and realize, naturally it is also possible to by firmly
Part.Based on such understanding, the portion that prior art is contributed by technique scheme the most in other words
Dividing and can embody with the form of software product, this computer software product can be stored in computer can
Read in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that one
Computer equipment (can be personal computer, server, or the network equipment etc.) performs each to be implemented
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, rather than to it
Limit;Although the present invention being described in detail with reference to previous embodiment, the ordinary skill of this area
Personnel it is understood that the technical scheme described in foregoing embodiments still can be modified by it, or
Person carries out equivalent to wherein portion of techniques feature;And these amendments or replacement, do not make corresponding skill
The essence of art scheme departs from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. an optimization method for disk buffering system, including:
Determine the history visitation frequency of each file in the first mechanical hard disk in described disk buffering system;
The file that history visitation frequency exceedes predetermined threshold is defined as focus file;
All Files in first mechanical hard disk is continuously written into the second mechanical hard disk, wherein, relative to institute
For having in file the residue file in addition to described focus file, the file data of described focus file from
Disk outer course road in disk preferentially writes described second mechanical hard disk;
Based on the file data in described described second mechanical hard disk being continuously written into All Files, generate magnetic
Disk mirroring;
Described disk mirroring is utilized to cover the file in described first mechanical hard disk.
Method the most according to claim 1, described disk buffering system also includes solid state hard disc, its
In, after the All Files in the first mechanical hard disk is continuously written into the second mechanical hard disk, also include: will
File metadata write solid state hard disc in described All Files.
Method the most according to claim 2, wherein, by the file unit number in described All Files
After write solid state hard disc, also include: will write less than the focus file of described solid state hard disc residual capacity
Enter described solid state hard disc.
4. according to the method described in claim 1 or 3, wherein, the writing mode of described focus file is
Write the most successively according to the history visitation frequency of focus file.
5. according to the method according to any one of claim 1-3, wherein, described determine described disk delay
The history visitation frequency of each file in the first mechanical hard disk in deposit system includes: periodically detect institute
State each file in the first mechanical hard disk when Autonomous test, to play the history in set time section forward access frequency
Secondary.
6. for the optimization system of disk buffering system, wherein, including:
History visitation frequency determines unit, for determining the first mechanical hard disk in described disk buffering system
In the history visitation frequency of each file;
Focus document determining unit, is defined as heat for history visitation frequency exceedes the file of predetermined threshold
Dot file;
Write control unit is hard for the All Files in the first mechanical hard disk is continuously written into the second machinery
Dish, wherein, for residue file in addition to described focus file in All Files, described heat
The file data of dot file preferentially writes described second mechanical hard disk from disk outer course road in disk;
Mirror image signal generating unit, for based in described described second mechanical hard disk being continuously written into All Files
File data, generate disk mirroring;
Data convert unit, for utilizing described disk mirroring to cover the file in described first mechanical hard disk.
Optimization system the most according to claim 6, described disk buffering system also includes solid state hard disc,
Wherein, said write control unit also includes:
Metadata writing module, for writing solid state hard disc by the file metadata in described All Files.
Optimization system the most according to claim 7, wherein, said write control unit also includes:
The focus file writing module being connected with described metadata writing module, being used for will be less than described solid-state
The focus file of hard disk remaining capacity writes described solid state hard disc.
9. according to the optimization system described in claim 6 or 8, wherein, said write control unit is also wrapped
Including: focus document input module, being used for the writing mode of focus file is the history according to focus file
Visitation frequency writes the most successively.
10. according to the optimization system described in any one of claim 6-8, wherein, described history accesses frequency
Secondary determine that unit rises when Autonomous test for periodically detecting each file in described first mechanical hard disk
History visitation frequency in set time section forward.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610184620.4A CN105892938A (en) | 2016-03-28 | 2016-03-28 | Optimization method and system of disk cache system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610184620.4A CN105892938A (en) | 2016-03-28 | 2016-03-28 | Optimization method and system of disk cache system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105892938A true CN105892938A (en) | 2016-08-24 |
Family
ID=57014261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610184620.4A Pending CN105892938A (en) | 2016-03-28 | 2016-03-28 | Optimization method and system of disk cache system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105892938A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108132759A (en) * | 2018-01-15 | 2018-06-08 | 网宿科技股份有限公司 | A kind of method and apparatus that data are managed in file system |
CN108804351A (en) * | 2018-05-30 | 2018-11-13 | 郑州云海信息技术有限公司 | A kind of caching replacement method and device |
CN110704336A (en) * | 2019-09-26 | 2020-01-17 | 北京神州绿盟信息安全科技股份有限公司 | Data caching method and device |
WO2021237645A1 (en) * | 2020-05-29 | 2021-12-02 | 深圳市欢太科技有限公司 | Method and apparatus for updating mirroring, and electronic device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419828A (en) * | 2008-11-20 | 2009-04-29 | 杭州海康威视数字技术股份有限公司 | Hard disc video recording and retrieval method for analog magnetic tape serial schema |
CN102194010A (en) * | 2011-06-16 | 2011-09-21 | 华中科技大学 | Zero-copy defragmentation method for virtual file system fragments |
CN103678180A (en) * | 2013-11-29 | 2014-03-26 | 武汉天喻信息产业股份有限公司 | Intelligent card nonvolatile memory management method |
US20140229657A1 (en) * | 2013-02-08 | 2014-08-14 | Microsoft Corporation | Readdressing memory for non-volatile storage devices |
CN104933169A (en) * | 2015-06-29 | 2015-09-23 | 南开大学 | File system defragmentation method based on hotspot file priority |
CN105373487A (en) * | 2015-12-16 | 2016-03-02 | 浪潮(北京)电子信息产业有限公司 | Defragmentation method and system for storage operation system |
-
2016
- 2016-03-28 CN CN201610184620.4A patent/CN105892938A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419828A (en) * | 2008-11-20 | 2009-04-29 | 杭州海康威视数字技术股份有限公司 | Hard disc video recording and retrieval method for analog magnetic tape serial schema |
CN102194010A (en) * | 2011-06-16 | 2011-09-21 | 华中科技大学 | Zero-copy defragmentation method for virtual file system fragments |
US20140229657A1 (en) * | 2013-02-08 | 2014-08-14 | Microsoft Corporation | Readdressing memory for non-volatile storage devices |
CN103678180A (en) * | 2013-11-29 | 2014-03-26 | 武汉天喻信息产业股份有限公司 | Intelligent card nonvolatile memory management method |
CN104933169A (en) * | 2015-06-29 | 2015-09-23 | 南开大学 | File system defragmentation method based on hotspot file priority |
CN105373487A (en) * | 2015-12-16 | 2016-03-02 | 浪潮(北京)电子信息产业有限公司 | Defragmentation method and system for storage operation system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108132759A (en) * | 2018-01-15 | 2018-06-08 | 网宿科技股份有限公司 | A kind of method and apparatus that data are managed in file system |
CN108132759B (en) * | 2018-01-15 | 2021-04-16 | 网宿科技股份有限公司 | Method and device for managing data in file system |
CN108804351A (en) * | 2018-05-30 | 2018-11-13 | 郑州云海信息技术有限公司 | A kind of caching replacement method and device |
CN108804351B (en) * | 2018-05-30 | 2021-10-29 | 郑州云海信息技术有限公司 | Cache replacement method and device |
CN110704336A (en) * | 2019-09-26 | 2020-01-17 | 北京神州绿盟信息安全科技股份有限公司 | Data caching method and device |
CN110704336B (en) * | 2019-09-26 | 2021-10-15 | 绿盟科技集团股份有限公司 | Data caching method and device |
WO2021237645A1 (en) * | 2020-05-29 | 2021-12-02 | 深圳市欢太科技有限公司 | Method and apparatus for updating mirroring, and electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9355112B1 (en) | Optimizing compression based on data activity | |
US9128855B1 (en) | Flash cache partitioning | |
US6615318B2 (en) | Cache management system with multiple cache lists employing roving removal and priority-based addition of cache entries | |
US8549526B2 (en) | Access control apparatus and access control method | |
US7565494B1 (en) | Configuring a bounded cache prefetch policy in a computer system employing object addressable storage | |
CN104834675A (en) | Query performance optimization method based on user behavior analysis | |
US7451225B1 (en) | Configuring a cache prefetch policy in a computer system employing object addressable storage | |
CN110019361B (en) | Data caching method and device | |
JP2008015623A (en) | Controller of storage system equipped with many kinds of storage devices | |
CN105892938A (en) | Optimization method and system of disk cache system | |
KR100954624B1 (en) | Method and system for providing content according to personal preference | |
JP7176209B2 (en) | Information processing equipment | |
JP2018005446A (en) | Information processing apparatus, storage control program, and storage control method | |
US20170004087A1 (en) | Adaptive cache management method according to access characteristics of user application in distributed environment | |
US20180196610A1 (en) | Database Memory Monitoring and Defragmentation of Database Indexes | |
US20090182957A1 (en) | Data storage apparatus | |
CN100458792C (en) | Method and data processing system for managing a mass storage system | |
US20180341423A1 (en) | Storage control device and information processing system | |
US9430168B2 (en) | Recording medium storing a program for data relocation, data storage system and data relocating method | |
CN102609363B (en) | A kind of aging method of caching server content and caching server | |
US10585802B1 (en) | Method and system for caching directories in a storage system | |
CN109582233A (en) | A kind of caching method and device of data | |
US10185660B2 (en) | System and method for automated data organization in a storage system | |
US20060015680A1 (en) | Apparatus and method for data storage, and computer product | |
CN110334073A (en) | A kind of metadata forecasting method, device, terminal, server and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160824 |