CN107784121A - Lowercase optimization method of log file system based on nonvolatile memory - Google Patents
Lowercase optimization method of log file system based on nonvolatile memory Download PDFInfo
- Publication number
- CN107784121A CN107784121A CN201711149326.0A CN201711149326A CN107784121A CN 107784121 A CN107784121 A CN 107784121A CN 201711149326 A CN201711149326 A CN 201711149326A CN 107784121 A CN107784121 A CN 107784121A
- Authority
- CN
- China
- Prior art keywords
- data
- page
- renewal
- metadata
- write
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/13—File access structures, e.g. distributed indices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search processing
- G06F16/152—File search processing using file content signatures, e.g. hash values
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/1727—Details of free space management performed by the file system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/1805—Append-only file systems, e.g. using logs or journals to store data
- G06F16/1815—Journaling file systems
Abstract
The invention relates to a performance optimization method of a log file system based on a nonvolatile memory. The method comprises the steps that an NVM and a DRAM are connected to a CPU memory bus, in-place writing is used for updating small data so as to minimize memory occupation, fine-grained backup is carried out on the data to be updated by using a small data log, and the latest data information to be changed of a file is recorded; the global hash table is stored through a circular buffer with a fixed length, and the initial address of each update is recorded for quick indexing of the data page in the next in-place update. Recording the initial address of the updated data page for the next quick index of the data page; after the data writing is completed, the pointer of the metadata pointing to the data block is updated, and the journal is updated to submit the writing, so that the journal serves as a mark for the completion of the operation. The invention can balance the data consistency overhead and performance, reduce the space distribution cost, avoid the write-in amplification in the small data updating process and simultaneously provide strong data consistency guarantee.
Description
Technical field
The present invention relates to the performance optimization method of the JFS based on nonvolatile memory, especially for small data
The optimization method of write performance under more new scene.
Background technology
Several non-volatile memory technologies (non-volatile memory, NVM) are currently researched and developed, are wrapped
Include phase transition storage (PCM), ferroelectric memory (FeRAM), memristor (Memristors), spin-transfer torque memory (STT-
) and 3D XPoint etc. RAM.These NVM have capacity is big, integrated level is high, electricity leakage power dissipation is low, access speed is fast, it is non-volatile,
Can byte addressing the advantages that.Due to NVM both with DRAM can byte addressing characteristic, again have disk persistence, data
The persistence of memory hierarchy can be realized in NVM.Persistence internal memory originally by RAMDISK form simulation block devices, with
Compatible traditional file systemses, so that it benefits from the persistence of memory hierarchy.However, traditional file systemses can not fit completely
For NVMM, mainly there are two reasons：First, traditional file systemses due to disk block addressing characteristic generally by block come tissue and
Data are managed, can not be addressed when applied to NVM using NVM byte to improve system read-write performance.Secondly, traditional file system
The done most of optimization of system be all premised on the order read-write of disk, but NVM in random and order read-write not
Very big performance difference.Therefore, if using traditional file systemses for NVM, its data management mode will give systematic function
Bring redundancy and burden.Therefore, current file system all crosses caching of page and directly handles NVM by rambus access
Device, NVM is accessed with byte granularity by processor, so as to build persistence memory file system.
For persistence memory file system, CPU directly to access NVM around DRAM page cache, is stored in NVM
Data to must assure that uniformity is only effective and addressable.And CPU and its caching level can reorder to operation
With improving performance.In order to reach this point, the operation of file system must be atomicity, operated to prevent locking system all
Data structure, which is produced, into preceding collapse is in inconsistent state.The file system of main flow overcomes collapse using some mechanism at present
Consistency problem, such as journaling, copy-on-write (COW) and log-structured.However, this several method is all present
Defect.Journaling can perform to each write operation prevents loss of data twice, and COW is first multiple when being updated to data
Original data block is made to be modified again, this can be produced for small renewal writes amplification, it is log-structured be will update it is advanced
After row caching, target location is uniformly written to, this needs the continuous space of bulk in caching.
In addition, changed by the access mode for paying close attention to file under different scenes, it can be found that the read-write operation meeting of small documents
Performance boost to file system produces important influence.Traditional block device is read and write for small documents due to block addressing and order
It is limited all the time in the performance boost of read-write and small renewal.With NVM appearance, our cans apply the property such as its byte addressing
Data layout can be reconfigured, optimize access strategy, so as to realize the high performance file system for NVM, particularly pair
In the centrally updated application scenarios of small data.
The content of the invention
In order to solve above-mentioned technical problem, it is an object of the invention to provide a kind of daily record text based on nonvolatile memory
The small letter optimization method of part system.NVM and DRAM are connected on CPU rambus by this method, and small data is updated using former
Ground is write so as to minimize EMS memory occupation, carries out fine-grained backup to the data to be updated using small data daily record, record is hereafter
The newest data message to be changed of part；By the cyclic buffer of a regular length, global Hash table is deposited, is recorded
The initial address each updated, to the quick indexing of this data page when being updated for original place next time.Record and update the data
The initial address of page, for next time to the quick indexing of this data page；After the completion of data write-in, pointed to by more new metadata
The pointer of data block, Update log tail is to specifically writing into capable submission, the mark as this operation completion.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of small letter optimization method of the JFS based on nonvolatile memory, including：
The first step, system is arranged side by side with DRAM by NVM, is directly connected on CPU rambus, CPU is come to visit using load and store
Ask NVM so that NVM is present in internal memory level rather than block device level, and the performance for fundamentally realizing persistence internal memory carries
Rise；
Data and daily record are deposited in NVM by second step, system with list structure respectively, each inode using single daily record with
Support concurrently accesses.Data directory is deposited in into DRAM in the form of radix tree and supports quick search.Data are distributed based on page,
The size for giving tacit consent to a data page is 4096 bytes (4KB)；
3rd step, when data have renewal to operate, calculate and this time update involved data number of pages, when renewal is more than file system
During one data page size of system, the 7th step is leapt to；
4th step, when renewal is less than a data page size, metadata record is first added to daily record.In DRAM, we
House the global Hash table of a recyclable write-in.When writing individual data page first, a new page is distributed, in Hash table
The block number and initial address of middle record new data page.Hash table quick indexing to ground can be passed through when writing this data page again next time
Location；
5th step, fine-grained backup first is carried out to the data to be updated, i.e., can not be in Hash by block number if writing first
Data page address is found in table, then initial data is first copied into new page, then write and update the data；If can direct rope in Hash table
Data page address is guided to, then the newest data message to be changed of file be recorded into small data Log backup.Then logarithm
Renewal is write according to page progress original place；
6th step, after renewal terminates, more new metadata points to the pointer of data block, and Update log tail carries to current row of writing into
Hand over, represent that this time renewal is completed, the pointer of final updating index of metadata；
7th step, the renewal of writing for multiple data pages, the data of change part are first write in newly assigned space, then not more
The former data duplication changed is to the new page, and after data write-in terminates, our more new metadatas simultaneously point to corresponding daily record entry
New page, Update log tail are submitted, and represent the completion of this time renewal, the pointer of final updating index of metadata.
It can reach following beneficial effect using the present invention：First, it is different from traditional storage device to take full advantage of NVM for it
Byte addressing characteristic, structure and DRAM and NVM mixing memory.Secondly, the present invention can be with balance data coherency expense
And performance, space apportioning cost is reduced, avoids the write-in in small data renewal process from amplifying, lifting system write performance, simultaneously
Powerful data consistency is provided after system crash to ensure.
Brief description of the drawings
Fig. 1 is the small letter flow chart of the JFS based on nonvolatile memory；
Fig. 2 is small data renewal structural representation.
Embodiment
Reference picture 1, the invention provides a kind of optimization of the small letter of JFS based on nonvolatile memory, including:
The first step, system is arranged side by side with DRAM by NVM, is directly connected on CPU rambus, CPU is come to visit using load and store
Ask NVM.Caching is crossed using copy_from_user_nocache () interface, it is ensured that the data to be write are repaiied in associated metadata
Persistence has been carried out before changing；
Data and metadata are deposited in NVM by second step, system with list structure respectively, and each inode uses single daily record
To support concurrently to access.Index of metadata is deposited in into DRAM in the form of radix tree and supports quick search.Data are based on page
Distribution, the size of one data page of acquiescence is 4096 bytes (4KB)；
3rd step, when data have renewal to operate, calculate this time update involved data number of pages first.When renewal is more than text
During one data page size of part system, the 7th step is leapt to；
4th step, when renewal is less than a data page size, metadata record is first added to daily record, in DRAM, there is one
The global Hash table of individual recyclable write-in.When writing individual data page first, a new page is distributed, number is recorded in Hash table
According to the block number and initial address of page.Can be by Hash table quick indexing to address when writing this data page again next time；
5th step, fine-grained backup first is carried out to the data to be updated, i.e., can not be in Hash by block number if writing first
Data page address is found in table, then initial data is first copied into new page, then write and update the data；If can direct rope in Hash table
Data page address is guided to, then the newest data message to be changed of file be recorded into small data Log backup.Then logarithm
Renewal is write according to page progress original place；
6th step, after renewal terminates, more new metadata points to the pointer of data block, and Update log tail carries to current row of writing into
Hand over, represent that this time renewal is completed, the pointer of final updating index of metadata.Fig. 2 is signal when data page 0 is updated
Figure,<0,1>Represent since data page 0, the data of renewal are related to number of pages for 1；
7th step, the renewal of writing for multiple data pages, the data of change part are first write in newly assigned space, then not more
The former data duplication changed is to the new page.After data write-in terminates, our more new metadatas simultaneously point to corresponding daily record entry
New page, Update log tail are submitted, and represent the completion of this time renewal, the pointer of final updating index of metadata.
Preferred embodiment is further used as, described step two, it is specially：
For metadata, the log-structured file system usage log of selection records the operation each time of metadata,
Each renewal of metadata can all add a daily record entry, and we are by changing daily record tail to newest after the updating
Entry updates to submit, and we support the atomic write of 64 at default processor, therefore can ensure the atomicity of renewal.Data
Page size may have 4KB, 2MB and 1GB according to different processor, and it is 4KB that we, which give tacit consent to it, herein；
Preferred embodiment is further used as, before described step four：
When judging that renewal is within a data page, metadata record is first added to daily record, write-in is recycled in DRAM
Global Hash table, the data page address of recent renewal is stored using the confined space.When this data page is to update first, distribution
One new page, the block number and initial address of record data page in Hash table.Hash can be passed through when writing this page again next time
Table quick indexing is to its initial address；
Preferred embodiment is further used as, during described step five, six：
Before data are write, each inode can have the data record of latest update, including inclined in the page of change data
Shifting amount and length records.For the data page that can be found in Hash table, one fixed small data daily record of distribution to it is each more
New data records carry out fine-grained backup, and it is lasting that data are brushed out into progress from cpu cache using clflush and mfence
Change, then carry out original place to data page again writes renewal.Relative to multiple data page distribution in clone method during conventional write and
The repetition of unmodified data is write, and makes the write performance that can improve small data in this way.After system crash or power-off, read small
Data in data logging carry out redo, so as to complete the operation do not submitted, prevent data to be in inconsistent state.
Preferred embodiment is further used as, in described step seven, it is specially：
It is related to multiple pages when judging that data update, the data of change part is write in newly assigned space, then the original do not changed
For data duplication to the new page, more new metadata and daily record entry point to the pointer of new page, and Update log tail carries out this
The submission of secondary renewal.System can so be ensured once being collapsed in reproducting periods, as long as metadata daily record tail is not submitted, I
Original data page still can be found according to old metadata, so as to ensure that data are in the state of uniformity.
Above is the preferable implementation to the present invention is illustrated, but the invention is not limited to the implementation
Example, those skilled in the art can also make a variety of equivalent variations on the premise of without prejudice to spirit of the invention or replace
Change, these equivalent modifications or replacement are all contained in the application claim limited range.
Claims (5)
1. a kind of small letter optimization method of the JFS based on nonvolatile memory, it is characterised in that connect NVM and DRAM
It is connected on CPU rambus, small data is updated and write using original place so as to minimize EMS memory occupation, using small data daily record to wanting
The data of renewal carry out fine-grained backup, record the newest data message to be changed of file；It is slow by a circulation
Area is rushed, deposits global Hash table, records the initial address of each renewal, to this data page when being updated for original place next time
Quick indexing；The initial address for updating the data page is recorded, for next time to the quick indexing of this data page；Data write
After the completion of, the pointer of data block is pointed to by more new metadata, Update log tail is to specifically writing into capable submission, as this behaviour
Make the mark completed；Comprise the following steps：
The first step, system is arranged side by side with DRAM by NVM, is directly connected on CPU rambus, CPU is come to visit using load and store
Ask NVM so that NVM is present in internal memory level rather than block device level, realizes the performance boost of internal memory；
Data and metadata are deposited in NVM by second step, system with list structure respectively, and each inode uses single daily record
To support concurrently to access, index of metadata is deposited in into DRAM in the form of radix tree and supports quick lookup, data are based on page
Distribution, the size of one data page of acquiescence is 4096 bytes；
3rd step, when data have renewal to operate, calculate this time update involved data number of pages first, when renewal is more than text
During one data page size of part system, the 7th step is leapt to；
4th step, when renewal is less than a data page size, metadata record is first added to log, in DRAM, there is one
The global Hash table of recyclable write-in, when writing individual data page first, distribute a new page, the record data in Hash table
The block number and initial address of page, when writing this data page again next time by Hash table quick indexing to address；
5th step, fine-grained backup first is carried out to the data to be updated, i.e., can not be in Hash by block number if writing first
Data page address is found in table, then initial data is first copied into new page, then write and update the data；If direct index in Hash table
To data page address, then the newest data message to be changed of file be recorded into small data Log backup, then to data
Write renewal in page progress original place；
6th step, after renewal terminates, more new metadata points to the pointer of data block, and Update log tail carries to current row of writing into
Hand over, represent that this time renewal is completed, the pointer of final updating index of metadata；
7th step, the renewal of writing for multiple data pages, the data of change part are first write in newly assigned space, then not more
The former data duplication changed is to the new page, and after data write-in terminates, our more new metadatas simultaneously point to corresponding daily record entry
New page, Update log tail are submitted, and represent the completion of this time renewal, the pointer of final updating index of metadata.
2. a kind of small letter optimization method of JFS based on nonvolatile memory according to claim 1, it is special
Sign is that, in described second step, it is specially：
For metadata, the log-structured file system usage log of selection records the operation each time of metadata,
Each renewal of metadata can all add a daily record entry, and we are by changing daily record tail to newest after the updating
Entry updates to submit.
3. a kind of small letter optimization method of JFS based on nonvolatile memory according to claim 1, it is special
Sign is, the 4th described step：
When judging that renewal is within a data page, metadata record is first added to log, in DRAM, has one can follow
The global Hash table of ring write-in, the data page address of recent renewal is stored using the confined space, when this data page is to update first
When, a new page is distributed, the block number and initial address of record data page, pass through when writing this page again next time in Hash table
Hash table quick indexing is to its initial address.
4. a kind of small letter optimization method of JFS based on nonvolatile memory according to claim 1, it is special
Sign is, in the 5th described step, six-step process, in addition to：
Before data are write, each inode can have the data record of latest update, including inclined in the page of change data
Shifting amount and length records, for the data page found in Hash table, one fixed small data daily record of distribution is to each renewal
Data record carries out fine-grained backup, and data are brushed out into carry out persistence from cpu cache using clflush and mfence,
Then carry out original place to data page again writes renewal, makes the write performance for improving small data in this way, in system crash or disconnected
After electricity, the data read in small data daily record carry out redo, so as to complete the operation do not submitted, prevent that data are inconsistent
State.
5. a kind of small letter optimization method of JFS based on nonvolatile memory according to claim 1, it is special
Sign is that, in the 7th described step, it is specially：
It is related to multiple pages when judging that data update, the data of change part is write in newly assigned space, then the original do not changed
For data duplication to the new page, more new metadata and daily record entry point to the pointer of new page, and Update log tail carries out this
The submission of secondary renewal, ensure system once being collapsed in reproducting periods, still can basis as long as metadata daily record tail is not submitted
Old metadata finds original data page, so as to ensure that data are in the state of uniformity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711149326.0A CN107784121B (en) | 2017-11-18 | 2017-11-18 | Lowercase optimization method of log file system based on nonvolatile memory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711149326.0A CN107784121B (en) | 2017-11-18 | 2017-11-18 | Lowercase optimization method of log file system based on nonvolatile memory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784121A true CN107784121A (en) | 2018-03-09 |
| CN107784121B CN107784121B (en) | 2020-04-24 |
Family
ID=61433381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711149326.0A Active CN107784121B (en) | 2017-11-18 | 2017-11-18 | Lowercase optimization method of log file system based on nonvolatile memory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107784121B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508143A (en) * | 2018-08-17 | 2019-03-22 | 郑州云海信息技术有限公司 | A kind of date storage method and device |
| CN110134657A (en) * | 2019-04-08 | 2019-08-16 | 中国科学院计算技术研究所 | File system metadata based on non-volatile main memory operates acceleration method and system |
| CN110377531A (en) * | 2019-07-19 | 2019-10-25 | 清华大学 | Based on log-structured persistence memory storage engine apparatus and control method |
| CN110688357A (en) * | 2018-06-20 | 2020-01-14 | 华为技术有限公司 | Method and device for reading log type data |
| CN111240840A (en) * | 2020-01-09 | 2020-06-05 | 中国人民解放军国防科技大学 | Nonvolatile memory data consistency updating method based on one-to-many page mapping |
| CN113486399A (en) * | 2021-07-14 | 2021-10-08 | 上海瓶钵信息科技有限公司 | Data storage method and system based on RISC-V architecture |
| CN113655949A (en) * | 2020-06-15 | 2021-11-16 | 中兴通讯股份有限公司 | Database page caching method and system based on PM |
| CN113935476A (en) * | 2021-12-16 | 2022-01-14 | 之江实验室 | Deep learning data set access method and system, electronic equipment and storage medium |
| CN114281762A (en) * | 2022-03-02 | 2022-04-05 | 苏州浪潮智能科技有限公司 | Log storage acceleration method, device, equipment and medium |
| CN114461456A (en) * | 2022-04-11 | 2022-05-10 | 成都云祺科技有限公司 | CDP backup method, system, storage medium and recovery method based on continuous writing |
| CN114510198A (en) * | 2022-02-16 | 2022-05-17 | 北京中电华大电子设计有限责任公司 | Method for improving erasing and writing efficiency of NVM |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103392207A (en) * | 2011-10-05 | 2013-11-13 | Lsi公司 | Self-journaling and hierarchical consistency for non-volatile storage |
| CN106599096A (en) * | 2016-11-24 | 2017-04-26 | 上海交通大学 | High-performance file system designing method based on non-volatile memory |
| US20170160988A1 (en) * | 2015-12-08 | 2017-06-08 | Kabushiki Kaisha Toshiba | Memory system that carries out an atomic write operation |
| CN106843772A (en) * | 2017-02-14 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of system and method based on uniformity bus extension nonvolatile memory |
| CN107329696A (en) * | 2017-06-23 | 2017-11-07 | 华中科技大学 | A kind of method and system for ensureing data corruption uniformity |
-
2017
- 2017-11-18 CN CN201711149326.0A patent/CN107784121B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103392207A (en) * | 2011-10-05 | 2013-11-13 | Lsi公司 | Self-journaling and hierarchical consistency for non-volatile storage |
| US20170160988A1 (en) * | 2015-12-08 | 2017-06-08 | Kabushiki Kaisha Toshiba | Memory system that carries out an atomic write operation |
| CN106599096A (en) * | 2016-11-24 | 2017-04-26 | 上海交通大学 | High-performance file system designing method based on non-volatile memory |
| CN106843772A (en) * | 2017-02-14 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of system and method based on uniformity bus extension nonvolatile memory |
| CN107329696A (en) * | 2017-06-23 | 2017-11-07 | 华中科技大学 | A kind of method and system for ensureing data corruption uniformity |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688357A (en) * | 2018-06-20 | 2020-01-14 | 华为技术有限公司 | Method and device for reading log type data |
| CN110688357B (en) * | 2018-06-20 | 2021-08-20 | 华为技术有限公司 | Method and device for reading log type data |
| CN109508143B (en) * | 2018-08-17 | 2022-04-22 | 郑州云海信息技术有限公司 | Data storage method and device |
| CN109508143A (en) * | 2018-08-17 | 2019-03-22 | 郑州云海信息技术有限公司 | A kind of date storage method and device |
| CN110134657A (en) * | 2019-04-08 | 2019-08-16 | 中国科学院计算技术研究所 | File system metadata based on non-volatile main memory operates acceleration method and system |
| CN110377531A (en) * | 2019-07-19 | 2019-10-25 | 清华大学 | Based on log-structured persistence memory storage engine apparatus and control method |
| CN111240840A (en) * | 2020-01-09 | 2020-06-05 | 中国人民解放军国防科技大学 | Nonvolatile memory data consistency updating method based on one-to-many page mapping |
| CN111240840B (en) * | 2020-01-09 | 2022-03-22 | 中国人民解放军国防科技大学 | Nonvolatile memory data consistency updating method based on one-to-many page mapping |
| CN113655949A (en) * | 2020-06-15 | 2021-11-16 | 中兴通讯股份有限公司 | Database page caching method and system based on PM |
| WO2021254332A1 (en) * | 2020-06-15 | 2021-12-23 | 中兴通讯股份有限公司 | Pm-based database page caching method and system |
| CN113655949B (en) * | 2020-06-15 | 2023-12-01 | 中兴通讯股份有限公司 | PM-based database page caching method and system |
| CN113486399A (en) * | 2021-07-14 | 2021-10-08 | 上海瓶钵信息科技有限公司 | Data storage method and system based on RISC-V architecture |
| CN113935476A (en) * | 2021-12-16 | 2022-01-14 | 之江实验室 | Deep learning data set access method and system, electronic equipment and storage medium |
| CN114510198A (en) * | 2022-02-16 | 2022-05-17 | 北京中电华大电子设计有限责任公司 | Method for improving erasing and writing efficiency of NVM |
| CN114510198B (en) * | 2022-02-16 | 2023-06-30 | 北京中电华大电子设计有限责任公司 | Method for improving erasing and writing efficiency of NVM (non-volatile memory) |
| CN114281762A (en) * | 2022-03-02 | 2022-04-05 | 苏州浪潮智能科技有限公司 | Log storage acceleration method, device, equipment and medium |
| CN114461456A (en) * | 2022-04-11 | 2022-05-10 | 成都云祺科技有限公司 | CDP backup method, system, storage medium and recovery method based on continuous writing |
| CN114461456B (en) * | 2022-04-11 | 2022-06-21 | 成都云祺科技有限公司 | CDP backup method, system, storage medium and recovery method based on continuous writing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784121B (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784121A (en) | Lowercase optimization method of log file system based on nonvolatile memory | |
| CN104903872B (en) | System, method and interface for adaptive persistence | |
| US9298384B2 (en) | Method and device for storing data in a flash memory using address mapping for supporting various block sizes | |
| US9342256B2 (en) | Epoch based storage management for a storage device | |
| US8386698B2 (en) | Data accessing method for flash memory and storage system and controller using the same | |
| US20200117368A1 (en) | Method for achieving data copying in ftl of solid state drive, system and solid state drive | |
| US11210020B2 (en) | Methods and systems for accessing a memory | |
| US10296250B2 (en) | Method and apparatus for improving performance of sequential logging in a storage device | |
| US10740251B2 (en) | Hybrid drive translation layer | |
| CN103902669B (en) | A kind of separate type file system based on different storage mediums | |
| CN105335098A (en) | Storage-class memory based method for improving performance of log file system | |
| CN107329696B (en) | A kind of method and system guaranteeing data corruption consistency | |
| US11397669B2 (en) | Data storage device and non-volatile memory control method | |
| US11237980B2 (en) | File page table management technology | |
| CN111488125B (en) | Cache Tier Cache optimization method based on Ceph cluster | |
| US11307979B2 (en) | Data storage device and non-volatile memory control method | |
| CN109165321A (en) | A kind of consistency Hash table construction method and system based on nonvolatile memory | |
| CN108431784A (en) | Access request processing method, device and computer system | |
| TWI745987B (en) | Data storage device and non-volatile memory control method | |
| US11586353B2 (en) | Optimized access to high-speed storage device | |
| KR101618999B1 (en) | Network boot system | |
| Mao et al. | A DAX-enabled mmap mechanism for log-structured in-memory file systems | |
| US20210165598A1 (en) | Data storage device and non-volatile memory control method | |
| WO2024060944A1 (en) | Key value storage method and system | |
| CN117806570A (en) | Online memory expansion method, device, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |