CN108959500A - A kind of object storage method, device, equipment and computer readable storage medium - Google Patents
A kind of object storage method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108959500A CN108959500A CN201810669104.XA CN201810669104A CN108959500A CN 108959500 A CN108959500 A CN 108959500A CN 201810669104 A CN201810669104 A CN 201810669104A CN 108959500 A CN108959500 A CN 108959500A
- Authority
- CN
- China
- Prior art keywords
- reading
- fragmentation
- aggregate file
- total data
- aggregate
- 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
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0253—Garbage collection, i.e. reclamation of unreferenced memory
- G06F12/0261—Garbage collection, i.e. reclamation of unreferenced memory using reference counting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F12/12—Replacement control
- G06F12/121—Replacement control using replacement algorithms
- G06F12/123—Replacement control using replacement algorithms with age lists, e.g. queue, most recently used [MRU] list or least recently used [LRU] list
Abstract
The invention discloses a kind of object storage method, device, equipment and computer readable storage mediums, wherein this method comprises: reading the total data fragment for belonging to same target being stored in different aggregate files;Judge whether the quantity of the fragmentation of data read is greater than amount threshold, if it is, total data fragment is written back in the same aggregate file for reading, if it is not, then determining it is not necessary that the fragmentation of data to be written back in the same aggregate file.In technical solution of the present invention, reading object on read operation when extend to performance and influence serious when the total data fragment of object is written back in an aggregate file, by reading object in this aggregate file relative to by reading the time delay for obtaining object and greatly reducing read operation in multiple aggregate files respectively, the performance of read operation is improved.
Description
Technical field
The present invention relates to technical field of data storage, more specifically to a kind of object storage method, device, equipment
And computer readable storage medium.
Background technique
In distributed memory system, native object storage is located at the bottom, at present the native object storage engines of mainstream
It for FileStore, is realized based on local xfs file system, object data (data of native object) is stored in one admittedly
Determine in the file of size and (be defaulted as 4MB), the meta-data preservation of native object is independent in the extended attribute of file or local
In KV database.After system runs a period of time, a large amount of obj ect file (the corresponding file of native object) can be stored on disk.
On the basis of FileStore, reduce the number of obj ect file in such a way that object polymerize, while by small text
The random IO of part becomes linear IO, modification is write to become to add and be write, and improves the write-in of data under mass small documents scene
Energy.But this mode sacrifices reading performance in some scenarios, since all object datas within the same time are all chased after
Add and write in the same aggregate file, and write operation concurrently executes, leads to the different number of objects of the same native object
According to that can be written in multiple and different aggregate files, under the scene of fritter random read-write, this phenomenon is especially apparent.So exist
It when needing to realize the reading of native object, then needs to obtain the index information of native object, includes local right in the index information
As there is several fragmentation of data, offset and length of each fragmentation of data in native object, the number of place aggregate file and
The information such as offset;Then fragmentation of data is read from each aggregate file respectively, is returned after merging.This mode causes to read to grasp
The time delay of work is got higher, reduced performance.
In conclusion reading that there are the time delays of read operation is higher, performance is lower for native object in the prior art
Problem.
Summary of the invention
The object of the present invention is to provide a kind of object storage method, device, equipment and computer readable storage mediums, with solution
The certainly problem that the time delay of read operation existing for the reading for native object is higher, performance is lower in the prior art.
To achieve the goals above, the invention provides the following technical scheme:
A kind of object storage method, comprising:
Read the total data fragment for belonging to same target being stored in different aggregate files;
Judge whether the quantity of the fragmentation of data read is greater than amount threshold, if it is, total data fragment is returned
It writes for reading in the same aggregate file, if it is not, then determining it is not necessary that the fragmentation of data is written back to the same polymerization text
In part.
Preferably, it after reading the total data fragment for belonging to same target being stored in different aggregate files, also wraps
It includes:
Judge whether the access to the object is in the scene of write once read many, if it is, total data fragment is returned
It writes for reading in the same aggregate file, if it is not, then determining it is not necessary that the fragmentation of data is written back to the same polymerization text
In part.
Preferably, it after reading the total data fragment for belonging to same target being stored in different aggregate files, also wraps
It includes:
Judge whether the current load value of storage system belonging to the object is less than default load value, if it is, will
Total data fragment is written back in the same aggregate file for reading, and is not necessarily to if it is not, then determining by the fragmentation of data write-back
Into the same aggregate file.
Preferably, after total data fragment being written back in the same aggregate file, further includes:
It sets the index information of the object to the fragmentation of data is written to the location information of aggregate file extremely.
Preferably, it after reading the total data fragment for belonging to same target being stored in different aggregate files, also wraps
It includes:
By total data fragment store into caching for reading, the storage rule of the caching is the storage when the caching
When space is fully occupied, the data farthest used apart from current time stored in the caching are deleted.
Preferably, after by total data fragment store into caching, further includes:
Read requests corresponding with the object are received, judge whether be stored with the object in the caching, if so,
Then the object stored in the caching is returned, if it is not, then by the fragmentation of data to be written in aggregate file extremely
It obtains the object and returns.
A kind of object storage device, comprising:
Read module is used for: reading the total data fragment for belonging to same target being stored in different aggregate files;
Quantity judgment module, is used for: judge whether the quantity of the fragmentation of data read is greater than amount threshold, if so,
Then total data fragment is written back in the same aggregate file for reading, is not necessarily to if it is not, then determining by the fragmentation of data
It is written back in the same aggregate file.
Preferably, further includes:
Scene judgment module, is used for: it is broken to read the total data for belonging to same target being stored in different aggregate files
After piece, judge whether the access to the object is in the scene of write once read many, if it is, by total data fragment write-back
Into the same aggregate file for reading, if it is not, then determining it is not necessary that the fragmentation of data is written back to the same aggregate file
In.
A kind of object storage device, comprising:
Memory, for storing computer program;
Processor, when for executing the computer program the step of realization any one as above object storage method.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
The step of as above any one object storage method is realized when computer program is executed by processor.
The present invention provides a kind of object storage method, device, equipment and computer readable storage medium, wherein this method
It include: the total data fragment for belonging to same target for reading and being stored in different aggregate files;Judge that the data read are broken
Whether the quantity of piece is greater than amount threshold, if it is, total data fragment is written back in the same aggregate file for reading,
If it is not, then determining it is not necessary that the fragmentation of data to be written back in the same aggregate file.In technical solution of the present invention, reading
After getting the total data fragment for belonging to same target being stored in different aggregate files, if the fragmentation of data read
Quantity is greater than amount threshold, i.e., needs in reading object by reading respectively in more aggregate file, it is believed that read the object
It is caused to read operation when extend to performance influence it is more serious, then total data fragment is written back to the same aggregate file
In, by can be read in this aggregate file, to be otherwise then not necessarily to for total data fragment being written back to together when reading next time
In one aggregate file.As a result, reading object on read operation when extend to performance and influence serious when by the total data of object
Fragment is written back in an aggregate file, by reading object in this aggregate file relative to by distinguishing in multiple aggregate files
Reading obtains the time delay that object greatly reduces read operation, improves the performance of read operation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of object storage method provided in an embodiment of the present invention;
Fig. 2 is a kind of specific implementation schematic diagram of object storage method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural schematic diagram of object storage device provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, can wrap it illustrates a kind of flow chart of object storage method provided in an embodiment of the present invention
It includes:
S11: the total data fragment for belonging to same target being stored in different aggregate files is read.
It should be noted that a kind of execution subject of object storage method provided in an embodiment of the present invention can be corresponding
Object executive device, and the device can be set in the management node of distributed memory system, therefore the embodiment of the present invention mentions
A kind of execution subject of the object storage method supplied may be the management node of distributed memory system.In addition, in the application
Object be native object abbreviation, and reading described in step S11 belong to the total data fragment of same target specifically can be with
Refer to the total data fragment for reading belong to the same target for the first time, reads the total data for belonging to same target for the first time as a result,
Subsequent operation is carried out after fragment, can guarantee that the subsequent reading to the same target is all made of easy mode and realizes.
Aggregate file and fragmentation of data are the correspondence concept pointed out in background technique, wherein object can be divided into more
A fragmentation of data.
S12: judging whether the quantity of the fragmentation of data read is greater than amount threshold, if it is, total data is broken
Piece is written back in the same aggregate file for reading, if it is not, then determining it is not necessary that fragmentation of data is written back to the same polymerization text
In part.
Wherein, amount threshold can be set according to actual needs, such as can be 3.Fragmentation of data, the i.e. category read
In same target fragmentation of data quantity if it is greater than amount threshold, then illustrate to need when reading in object by more poly-
The different data fragment for obtaining object in file is closed, and then leads to that the time delay of read operation is higher, performance is lower, it therefore, will be whole
Fragmentation of data is written back in an aggregate file for reading, can be when needing reading object next time by reading in an aggregate file
It takes, so that the time delay of read operation is lower, performance is higher;The fragmentation of data that reads, the fragmentation of data for belonging to same target
If quantity is not more than amount threshold, illustrate to need the difference by obtaining object in less aggregate file in reading object
Fragmentation of data, it is considered that caused by this case to read operation when extend to performance influence be it is sustainable, therefore,
It is not necessary that fragmentation of data is written back in the same aggregate file.
It should be noted that total data fragment, which is written back in the same aggregate file, can be total data fragment
It will merge in obtained object one aggregate file of write-in after being merged into an object, it can also be by total data fragment by acquisition
Sequencing be written in same aggregate file, other settings can also be carried out according to actual needs, in guarantor of the invention
Within the scope of shield.
In addition, total data fragment is written back to the polymerization text in the same aggregate file by write-back total data fragment
Part can be the current aggregate file for carrying out write operation, specifically, when writing data into aggregate file, usually
First judge whether current aggregate file is write completely, if it is, being write using next new aggregate file as current aggregate file
Enter, if it is not, then current aggregate file is directly write data into, it is corresponding, as long as current aggregate file is not write in the application
It is full, then it can ignore the size of current aggregate file, and after all current aggregate file directly is written in total data fragment, then
It enables new aggregate file and realizes write operation.
In technical solution of the present invention, the whole numbers for belonging to same target being stored in different aggregate files are being read
After fragment, if the quantity of the fragmentation of data read is greater than amount threshold, i.e., need to be gathered by more in reading object
Close and read respectively in file, it is believed that read caused by the object to read operation when extend to performance influence it is more serious, then will be complete
Portion's fragmentation of data is written back in the same aggregate file, with next time read when by can be read in this aggregate file, it is no
Then it is not necessary that total data fragment to be written back in the same aggregate file.As a result, reading object to read operation when extend to
The total data fragment of object is written back in an aggregate file when performance influences serious, by being read in this aggregate file
Object improves read operation relative to by reading the time delay for obtaining object and greatly reducing read operation in multiple aggregate files respectively
Performance.
In addition, if the quantity of the fragmentation of data read be not more than amount threshold, i.e., in reading object need by compared with
Read respectively in few aggregate file, it is believed that read caused by the object to read operation when extend to performance influence it is slighter,
Then it is not necessary that total data fragment to be written back in the same aggregate file, the unnecessary occupancy for writing resource is avoided.
A kind of object storage method provided in an embodiment of the present invention, read be stored in different aggregate files belong to it is same
After the total data fragment of object, can also include:
Judge whether the access to object is in the scene of write once read many, if it is, total data fragment is written back to
For reading in the same aggregate file, if it is not, then determining it is not necessary that fragmentation of data to be written back in the same aggregate file.
Wherein, write once read many is identical as concept is corresponded in the prior art, refers generally to the end only one that write operation is carried out to object
It is a, but there are many end for carrying out read operation to object, no longer excessive explanation herein.If being currently in one to the access of object to write
The scene more read then illustrates to need the reading times to object more, then no matter the quantity of the total data fragment of object whether
Greater than amount threshold, then it is assumed that due to reading times cause more on read operation when extend to performance influence it is serious, will be whole
Fragmentation of data is written back in the same aggregate file for reading, and be further reduced the time delay of read operation, is improved read operation
Performance.
A kind of object storage method provided in an embodiment of the present invention, read be stored in different aggregate files belong to it is same
After the total data fragment of object, can also include:
Judge whether the current load value of storage system belonging to object is less than default load value, if it is, by whole
Fragmentation of data is written back in the same aggregate file for reading, if it is not, then determining same it is not necessary that fragmentation of data to be written back to
In aggregate file.
Wherein, default load value can be set according to actual needs, the load value of storage system in the prior art
Corresponding concept is identical, refers generally to the storage system currently occupied resource of ongoing operations and possessed all money
The ratio in source, naturally it is also possible to carry out other settings according to actual needs, be not specifically limited herein.If storage belonging to object
The current load value of system is less than default load value, then illustrates that storage system can have enough resources returning for fragmentation of data
It writes, total data fragment is written back in the same aggregate file for reading at this time, otherwise then illustrates that storage system is not enough
Resource for fragmentation of data write-back, there is no need to fragmentation of data is written back in the same aggregate file.To be according to storage
The loading condition of system determines whether fragmentation of data needs write-back, ensure that the reasonable occupancy of the resource of storage object.
It is further to note that the access that the fragmentation of data read is greater than amount threshold, object is in write once read many
Scene and object belonging to the current load value of storage system be less than in default this three conditions of load value, if one not
At least one of meet, then it is not necessary that fragmentation of data to be written back in the same aggregate file, if meet, by fragmentation of data write-back
Into the same aggregate file;Other conditions can certainly be set according to actual needs, protection scope of the present invention it
It is interior.
A kind of object storage method provided in an embodiment of the present invention, is written back to the same aggregate file for total data fragment
In after, can also include:
It sets the index information of object to fragmentation of data is written to the location information of aggregate file extremely.
Index information is updated to the location information for the aggregate file that total data fragment is written extremely, the index can be based on
Information quickly navigates to aggregate file and is read out object, can also include other content in certain index information, as object exists
The location informations such as the offset in aggregate file, it is within the scope of the present invention.
In addition, after total data fragment is written back to the same aggregate file, can also will be before fragmentation of data belonging to
Aggregate file in fragmentation of data delete, i.e., by step S11 read fragmentation of data when fragmentation of data belonging to aggregate file
In fragmentation of data delete, in order to avoid cause the waste in aggregate file space.
A kind of object storage method provided in an embodiment of the present invention, read be stored in different aggregate files belong to it is same
After the total data fragment of object, further includes:
By total data fragment store into caching for reading, the storage rule of caching is when the memory space of caching is complete
When portion occupies, the data farthest used apart from current time stored in caching are deleted.
It should be noted that the storage rule cached in the application is LRU, LRU is the contracting of Least Recently Used
It writes, i.e., it is least recently used, it is usually used in caching hot spot data, when data volume reaches the pre-set upper limit, automatically by those
Not used data are rejected at most, are vacateed memory headroom and are saved newest hot spot data.Namely when the memory space of caching is complete
When portion occupies, the data farthest used apart from current time stored in caching are deleted.So that the data in caching
For the current most desirable data, for reading.
A kind of object storage method provided in an embodiment of the present invention, after in total data fragment store extremely caching, also
May include:
Read requests corresponding with object are received, judge whether be stored with object in caching, if it is, by depositing in caching
The object of storage returns, if it is not, then by acquisition object in aggregate file extremely is written in fragmentation of data and is returned.
It, can be first by being read in caching, if there is no the object in caching, by gathering when needing to realize the reading of object
It closes and is read in file, to further speed up the reading of data.
As shown in Figure 2, wherein aggregate file 1 to aggregate file 6 is the different aggregate files in step S11, Jin Eryou
The fragmentation of data S0 to S5 for belonging to object is read in these different aggregate files, and aggregate file 7 is in above-described embodiment
New aggregate file extremely is written into total data fragment S0 to S5, thus by being initially required by aggregate file 1 to aggregate file 6
Fragmentation of data is obtained respectively, is changed into only by that can obtain total data fragment in this aggregate file of aggregate file 7, is reduced
The aggregate file quantity accessed is needed, the time delay of read operation is reduced, improves the performance of read operation.
The embodiment of the invention also provides a kind of object storage devices, as shown in figure 3, may include:
Read module 11, is used for: reading the total data fragment for belonging to same target being stored in different aggregate files;
Quantity judgment module 12, is used for: judge whether the quantity of the fragmentation of data read is greater than amount threshold, if
It is that then total data fragment is written back in the same aggregate file for reading, if it is not, then determining without returning fragmentation of data
It writes in the same aggregate file.
A kind of object storage device provided in an embodiment of the present invention can also include:
Scene judgment module, is used for: it is broken to read the total data for belonging to same target being stored in different aggregate files
After piece, judge whether the access to object is in the scene of write once read many, if it is, total data fragment is written back to together
For reading in one aggregate file, if it is not, then determining it is not necessary that fragmentation of data to be written back in the same aggregate file.
A kind of object storage device provided in an embodiment of the present invention can also include:
Load judgment module, is used for: it is broken to read the total data for belonging to same target being stored in different aggregate files
After piece, judge whether the current load value of storage system belonging to object is less than default load value, if it is, by whole numbers
It is written back in the same aggregate file according to fragment for reading, if it is not, then determining same poly- it is not necessary that fragmentation of data to be written back to
It closes in file.
A kind of object storage device provided in an embodiment of the present invention can also include:
Information setup module, is used for: after total data fragment is written back in the same aggregate file, by the rope of object
Fuse breath is set as that the location information of aggregate file extremely is written fragmentation of data into.
A kind of object storage device provided in an embodiment of the present invention, further includes:
Cache module is used for: read the total data fragment for belonging to same target that is stored in different aggregate files it
Afterwards, by, for reading, the storage rule of caching is when the memory space of caching is all accounted in total data fragment store extremely caching
Used time deletes the data farthest used apart from current time stored in caching.
A kind of object storage device provided in an embodiment of the present invention, further includes:
Ask respond module is used for: after in total data fragment store extremely caching, receiving reading corresponding with object
Request judges whether be stored with object in caching, if it is, the object stored in caching is returned, if it is not, then by that will count
It is written in aggregate file extremely according to fragment and obtains object and return.
The embodiment of the invention also provides a kind of object storage devices, may include:
Memory, for storing computer program;
Processor, when for executing computer program realize as above any one of object storage method the step of.
The embodiment of the invention also provides a kind of computer readable storage medium, it is stored on computer readable storage medium
Computer program, may be implemented when computer program is executed by processor as above any one of object storage method the step of.
It should be noted that a kind of object storage device provided in an embodiment of the present invention, equipment and computer-readable storage
The explanation of relevant portion refers to the detailed of corresponding part in a kind of object storage method provided in an embodiment of the present invention in medium
Illustrate, details are not described herein.In addition in above-mentioned technical proposal provided in an embodiment of the present invention with correspond to technical side in the prior art
The consistent part of case realization principle is simultaneously unspecified, in order to avoid excessively repeat.
The foregoing description of the disclosed embodiments can be realized those skilled in the art or using the present invention.To this
A variety of modifications of a little embodiments will be apparent for a person skilled in the art, and the general principles defined herein can
Without departing from the spirit or scope of the present invention, to realize in other embodiments.Therefore, the present invention will not be limited
It is formed on the embodiments shown herein, and is to fit to consistent with the principles and novel features disclosed in this article widest
Range.
Claims (10)
1. a kind of object storage method characterized by comprising
Read the total data fragment for belonging to same target being stored in different aggregate files;
Judge whether the quantity of the fragmentation of data read is greater than amount threshold, if it is, total data fragment is written back to
For reading in the same aggregate file, if it is not, then determining it is not necessary that the fragmentation of data to be written back in the same aggregate file.
2. being stored in belonging to a pair in different aggregate files the method according to claim 1, wherein reading
After the total data fragment of elephant, further includes:
Judge whether the access to the object is in the scene of write once read many, if it is, total data fragment is written back to
For reading in the same aggregate file, if it is not, then determining it is not necessary that the fragmentation of data to be written back in the same aggregate file.
3. according to the method described in claim 2, being stored in belonging to a pair in different aggregate files it is characterized in that, reading
After the total data fragment of elephant, further includes:
Judge whether the current load value of storage system belonging to the object is less than default load value, if it is, by whole
Fragmentation of data is written back in the same aggregate file for reading, if it is not, then determining it is not necessary that the fragmentation of data to be written back to together
In one aggregate file.
4. according to the method described in claim 3, it is characterized in that, total data fragment is written back in the same aggregate file
Later, further includes:
It sets the index information of the object to the fragmentation of data is written to the location information of aggregate file extremely.
5. according to the method described in claim 4, being stored in belonging to a pair in different aggregate files it is characterized in that, reading
After the total data fragment of elephant, further includes:
By total data fragment store into caching for reading, the storage rule of the caching is the memory space when the caching
When being fully occupied, the data farthest used apart from current time stored in the caching are deleted.
6. according to the method described in claim 5, it is characterized in that, also being wrapped after during total data fragment store is extremely cached
It includes:
Read requests corresponding with the object are received, judge whether be stored with the object in the caching, if it is, will
The object stored in the caching returns, if it is not, then being obtained by the fragmentation of data to be written in aggregate file extremely
The object simultaneously returns.
7. a kind of object storage device characterized by comprising
Read module is used for: reading the total data fragment for belonging to same target being stored in different aggregate files;
Quantity judgment module, is used for: judging whether the quantity of the fragmentation of data read is greater than amount threshold, if it is, will
Total data fragment is written back in the same aggregate file for reading, and is not necessarily to if it is not, then determining by the fragmentation of data write-back
Into the same aggregate file.
8. device according to claim 7, which is characterized in that further include:
Scene judgment module, is used for: read the total data fragment for belonging to same target that is stored in different aggregate files it
Afterwards, judge whether the access to the object is in the scene of write once read many, if it is, total data fragment is written back to together
For reading in one aggregate file, if it is not, then determining it is not necessary that the fragmentation of data to be written back in the same aggregate file.
9. a kind of object storage device characterized by comprising
Memory, for storing computer program;
Processor, realizing the object storage method as described in any one of claim 1 to 6 when for executing the computer program
Step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the step of the object storage method as described in any one of claim 1 to 6 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810669104.XA CN108959500A (en) | 2018-06-26 | 2018-06-26 | A kind of object storage method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810669104.XA CN108959500A (en) | 2018-06-26 | 2018-06-26 | A kind of object storage method, device, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108959500A true CN108959500A (en) | 2018-12-07 |
Family
ID=64486649
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810669104.XA Pending CN108959500A (en) | 2018-06-26 | 2018-06-26 | A kind of object storage method, device, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108959500A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134660A (en) * | 2019-05-22 | 2019-08-16 | 苏州浪潮智能科技有限公司 | A kind of data access method, device, equipment and computer readable storage medium |
CN111382129A (en) * | 2020-03-09 | 2020-07-07 | Oppo(重庆)智能科技有限公司 | File defragmentation method, device, storage medium and related equipment |
CN113126918A (en) * | 2021-04-01 | 2021-07-16 | 山东英信计算机技术有限公司 | Fragmented data reading method, device and medium |
WO2021147360A1 (en) * | 2020-01-21 | 2021-07-29 | 苏州浪潮智能科技有限公司 | Method, apparatus and device for processing asynchronous io data, and medium |
CN114327296A (en) * | 2021-12-31 | 2022-04-12 | 珠海豹好玩科技有限公司 | Intelligent disk fragment analysis method and device and electronic equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060053139A1 (en) * | 2004-09-03 | 2006-03-09 | Red Hat, Inc. | Methods, systems, and computer program products for implementing single-node and cluster snapshots |
CN101542588A (en) * | 2006-11-28 | 2009-09-23 | 索尼株式会社 | Mashing-up data file, mashing-up device and contents making-out method |
CN101576890A (en) * | 2008-05-08 | 2009-11-11 | 深圳市朗科科技股份有限公司 | Novel method and system for sorting fragment |
EP2326049A1 (en) * | 2006-03-31 | 2011-05-25 | Qualcomm Incorporated | Memory management for high speed media access control |
CN103778064A (en) * | 2012-10-23 | 2014-05-07 | 阿里巴巴集团控股有限公司 | Data management method and device |
CN105589812A (en) * | 2015-12-16 | 2016-05-18 | 成都华为技术有限公司 | Disk defragmentation method, disk defragmentation device and host |
CN106649860A (en) * | 2016-12-30 | 2017-05-10 | 郑州云海信息技术有限公司 | Defragmentation method applied to aggregation file |
CN107103009A (en) * | 2016-02-23 | 2017-08-29 | 杭州海康威视数字技术股份有限公司 | A kind of data processing method and device |
CN107204998A (en) * | 2016-03-16 | 2017-09-26 | 华为技术有限公司 | The method and apparatus of processing data |
-
2018
- 2018-06-26 CN CN201810669104.XA patent/CN108959500A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060053139A1 (en) * | 2004-09-03 | 2006-03-09 | Red Hat, Inc. | Methods, systems, and computer program products for implementing single-node and cluster snapshots |
EP2326049A1 (en) * | 2006-03-31 | 2011-05-25 | Qualcomm Incorporated | Memory management for high speed media access control |
CN101542588A (en) * | 2006-11-28 | 2009-09-23 | 索尼株式会社 | Mashing-up data file, mashing-up device and contents making-out method |
CN101576890A (en) * | 2008-05-08 | 2009-11-11 | 深圳市朗科科技股份有限公司 | Novel method and system for sorting fragment |
CN103778064A (en) * | 2012-10-23 | 2014-05-07 | 阿里巴巴集团控股有限公司 | Data management method and device |
CN105589812A (en) * | 2015-12-16 | 2016-05-18 | 成都华为技术有限公司 | Disk defragmentation method, disk defragmentation device and host |
CN107103009A (en) * | 2016-02-23 | 2017-08-29 | 杭州海康威视数字技术股份有限公司 | A kind of data processing method and device |
CN107204998A (en) * | 2016-03-16 | 2017-09-26 | 华为技术有限公司 | The method and apparatus of processing data |
CN106649860A (en) * | 2016-12-30 | 2017-05-10 | 郑州云海信息技术有限公司 | Defragmentation method applied to aggregation file |
Non-Patent Citations (2)
Title |
---|
刘应波: "太阳望远镜海量数据存储关键技术研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
胡永奎: "对象存储设备中文件系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134660A (en) * | 2019-05-22 | 2019-08-16 | 苏州浪潮智能科技有限公司 | A kind of data access method, device, equipment and computer readable storage medium |
WO2021147360A1 (en) * | 2020-01-21 | 2021-07-29 | 苏州浪潮智能科技有限公司 | Method, apparatus and device for processing asynchronous io data, and medium |
CN111382129A (en) * | 2020-03-09 | 2020-07-07 | Oppo(重庆)智能科技有限公司 | File defragmentation method, device, storage medium and related equipment |
CN111382129B (en) * | 2020-03-09 | 2023-09-22 | Oppo(重庆)智能科技有限公司 | File defragmentation method, device, storage medium and related equipment |
CN113126918A (en) * | 2021-04-01 | 2021-07-16 | 山东英信计算机技术有限公司 | Fragmented data reading method, device and medium |
CN113126918B (en) * | 2021-04-01 | 2023-02-28 | 山东英信计算机技术有限公司 | Fragmented data reading method, device and medium |
CN114327296A (en) * | 2021-12-31 | 2022-04-12 | 珠海豹好玩科技有限公司 | Intelligent disk fragment analysis method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108959500A (en) | A kind of object storage method, device, equipment and computer readable storage medium | |
CN109766312A (en) | A kind of block chain storage method, system, device and computer readable storage medium | |
KR101445481B1 (en) | File system hinting | |
CN105740164B (en) | Multi-core processor supporting cache consistency, reading and writing method, device and equipment | |
CN103377137B (en) | The frequent block strengthened detection is used to carry out the method and system of storage duplicate removal | |
CN102760101B (en) | SSD-based (Solid State Disk) cache management method and system | |
CN108647151A (en) | It is a kind of to dodge system metadata rule method, apparatus, equipment and storage medium entirely | |
CN107391398B (en) | Management method and system for flash memory cache region | |
CN108920387B (en) | Method and device for reducing read delay, computer equipment and storage medium | |
CN105183839A (en) | Hadoop-based storage optimizing method for small file hierachical indexing | |
CN110347336A (en) | A kind of key assignments storage system based on NVM with SSD mixing storage organization | |
CN104503703B (en) | The treating method and apparatus of caching | |
CN106528451B (en) | The cloud storage frame and construction method prefetched for the L2 cache of small documents | |
CN110188108A (en) | Date storage method, device, system, computer equipment and storage medium | |
CN108733306A (en) | A kind of Piece file mergence method and device | |
CN110727403A (en) | Metadata management method and device | |
CN109471843A (en) | A kind of metadata cache method, system and relevant apparatus | |
CN112799595B (en) | Data processing method, device and storage medium | |
CN104156323A (en) | Method and device for reading length of data block of cache memory in self-adaption mode | |
CN110888600A (en) | Buffer area management method for NAND flash memory | |
CN110442533A (en) | A kind of method, equipment and storage medium improving access performance | |
CN110147331A (en) | Caching data processing method, system and readable storage medium storing program for executing | |
CN110109845A (en) | Data cached management method, device, computer equipment and storage medium | |
CN115794669A (en) | Method, device and related equipment for expanding memory | |
CN107133183A (en) | A kind of cache data access method and system based on TCMU Virtual Block Devices |
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 |
Application publication date: 20181207 |
|
RJ01 | Rejection of invention patent application after publication |