CN106528001A - Cache system based on nonvolatile memory and software RAID - Google Patents
Cache system based on nonvolatile memory and software RAID Download PDFInfo
- Publication number
- CN106528001A CN106528001A CN201611106177.5A CN201611106177A CN106528001A CN 106528001 A CN106528001 A CN 106528001A CN 201611106177 A CN201611106177 A CN 201611106177A CN 106528001 A CN106528001 A CN 106528001A
- Authority
- CN
- China
- Prior art keywords
- raid
- cache
- metadata
- block
- data
- 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
- 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
- G06F3/0614—Improving the reliability of storage systems
-
- 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
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
-
- 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
- G06F3/0683—Plurality of storage devices
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
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)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention provides a cache system based on a nonvolatile memory and a software RAID. The cache system is characterized in that the cache system is a novel storage system architecture by fusing a nonvolatile memory Apache Pass, a software RAID, and a Device Mapper driving module Buaacache. According to the invention, the software RAID is managed by means of the Device Mapper mechanism of the Linux, a high-speed device Apache Pass serves as the Cache of a low-speed RAID, and therefore a two-stage cache system is constructed. The Persistent Memory is characterized in that after the Persistent Memory is powered off, medium data is not lost, and the read-write performance is excellent. According to the invention, the Persistent Memory is selected as the cache of the software RAID, under the condition that the cost is far lower than that of a hardware RAID, the read-write performance of the software RAID approaches even exceeds the hardware RAID.
Description
Technical field
The present invention relates to technical field of computer data storage, more particularly to a kind of new caching system, and in particular to arrive
New power down nonvolatile memory Persistent Memory and software RAID.
Background technology
With the rise of SSD, the storage system of main flow all gradually adopts the Bedding storage side that SSD is mixed with mechanical hard disk
Formula.Current storage scheme such as dm-cache, its design are based on Linux Device Mapper frameworks with realization, essence
On be general block device cache module, using SSD random read-writes performance it is good the characteristics of, using SSD as disk caching.With
SSD is compared, and (Persistent Memory, abbreviation PMEM are alternatively referred to as persistent storages to newborn nonvolatile memory
Device), with High Speed I/O, large storage capacity, power down it is non-volatile and can the excellent properties such as byte addressing, therefore propose a kind of base
In the new caching system of Persistent Memory and software RAID.
Nonvolatile memory：Persistent Memory, abbreviation PMEM, are characterized in that fully powered-off rear information is not lost
Lose.After ensure media data power down in addition to the characteristic do not lost, also with can byte addressing (Byte-addressable) and
The characteristics such as I/O superior performances.Under the pattern that writes back (write back), this kind equipment is different according to material, its write the consuming time,
The reading consuming time approaches DRAM, therefore very attractive as the cache of software RAID.Existing PMEM grinds
Study carefully scheme to focus mostly in hardware art, not yet have manufacturer and research institution to release the solution party with reference to PMEM with software RAID at present
Case is proposed.
AEP：Apache Pass, Intel Company are that the server platform " Purley " that will be released in 2017 is researched and developed
Persistent Memory of new generation, use as the caching of software RAID in caching system.
Software RAID：Software Redundant Arrays of Independent Disks, referred to as software independence
Redundant arrays of inexpensive disks, abbreviation software array.Compared with hardware RAID, software RAID does not need extrapolation RAID card to realize, but will
The bottom storage device of some mechanical hard disks or solid state hard disc etc, becomes a big virtual RAID with the polymerization of pure software form
Equipment.By PMEM as cache, software RAID can be on the premise of cost be far below hardware RAID, and aspect of performance is approached
Even more than the latter.Software is realized in the way of MD (Multiple Devices) Virtual Block Device at present in linux system
RAID, fictionalizes a new Virtual Block Device using the block device of multiple bottoms, and utilizes striping (stripping) skill
The readwrite performance that art is evenly distributed to data block on multiple disks to improve virtual unit.At present under linux, software RAID
Support RAID-0, RAID-1, RAID-4, RAID-5, RAID-6 and RAID-10.
Traditional software RAID scheme bottlenecks：The cpu performance and current loading of server are depended critically upon, pattern is being write back
Under, disconnection fault can cause the loss of data in internal memory and cannot recover, and compared with hardware RAID, advantage is not obvious.PMEM conducts
The popular new storage device risen in recent years, not yet has manufacturer and research institution to release at present and combines Persistent
The solution of Memory and software RAID, therefore the present invention is not from losing and I/O aspect of performances in power down media data
Persistent Memory that can be remarkable propose a kind of new and effective caching system as the cache of software RAID.
The content of the invention
The purpose of the present invention is the deficiency for traditional software RAID solutions in terms of power loss recovery and readwrite performance,
And for not yet having what nonvolatile memory (Persistent Memory, abbreviation PMEM) was combined with software RAID at present
Scheme is released, and is proposed a kind of based on PMEM and the caching system of software RAID.
Device Mapper Disk Mapping mechanism of the present invention based on Linux, developing kernel drive module Buaacache,
Using high-speed equipment PMEM as low speed RAID cache, so as to build a two-level cache system.
Low speed RAID with high speed PEME as a whole creation is by kernel-driven module Buaacache of the present invention
One virtual mixing block device, user can be as reading and writing common block device using mixing block device.It is slow in Virtual Block Device
Equipment PMEM and cache object RAID is deposited to invisible per family, with directly cannot accessing per family.User writable this new establishment
Virtual Block Device when, actual storing process is cached through Buaacache, if read-write hit directly in return cache
Data (or being written directly to caching), will otherwise read and write disk array.
The data space of buffer memory device PMEM of the present invention is divided into metadata space and data space, is connected using group and is reflected
Mode is penetrated, data space is divided into into the cache blocks of pre-defined size, cache blocks is combined as into one by fixed number further
Individual group (Set).The mapping relations one by one of certain cache blocks in metadata essential record hard disk block and a determination group, pass through
Distinctive byte addressing (Byte-addressable) modes of PMEM realize read-write.
The characteristic that the present invention is not lost by media data after PMEM device looses powers, compensate for tradition and writes back mechanism power down number
According to the defect lost, it is to avoid the multiple access to disk array, access time is greatly shortened.Using timely write-back internal memory unit number
According to mode, realize backing up in realtime metadata to buffer memory device during caching system runs, preserve system operation live.
After there is the loss of power accident, main frame can run scene by recovery system from buffer memory device after re-powering, it is to avoid dirty in caching
Data because lose with the corresponding relation of the disk block for being cached and disk cannot be write back to, realize power loss recovery function.
The present invention carries out secondary development from scheme d m-cache of increasing income, as dm-cache is used as Linux maturation kernels
A part, storage system plays the part of the role of caching at a slow speed for rear end can to adopt one or more fast equipments.But dm-
Cache latest editions only can on 3.10 version of kernel compilation run, kernel version span is excessive, and cause can not be steady in redaction
Determine normally to run on kernel.In view of not yet have new Kernel Porting version distribution at present, therefore the present invention has carried out specific aim transplanting
Work.
Description of the drawings
Fig. 1 caching system Linux I/O hierarchy charts；
Fig. 2 Buaacache drive module figures；
Fig. 3 caching system integrated stand compositions；
Fig. 4 buffer memory device Apache Pass structure charts；
Fig. 5 caching system mapping mode schematic diagrams；
Fig. 6 caching system read request schematic flow sheets；
Fig. 7 caching system write request schematic flow sheets；
Fig. 8 Kernel Porting operating diagrams；
Fig. 9 bio parts Kernel Porting schematic diagram；
Figure 10 Device Mapper parts Kernel Porting schematic diagram；
Specific embodiment
Must become more apparent to express the object, technical solutions and advantages of the present invention, below in conjunction with the accompanying drawings and specifically
The present invention is further described in more detail for embodiment.
The purpose of the present invention is easy in storage performance and power failure data for the disc array system for being currently based on software RAID
The deficiency of the aspects such as loss, proposes that one kind is based on nonvolatile memory (Persistent Memory, abbreviation PMEM) and software
The caching system of RAID.Device Mapper mechanism of the present invention based on Linux, developing kernel drive module Buaacache,
The PMEM device A pache Pass researched and developed using Intel, as the cache of low speed RAID.The software RAID exists
Complete to create by "-C " or "-create " parameter of mdadm softwares under Linux4.4 kernels, and be managed by mdadm.
Level of the present invention in Linux I/O systems is as shown in Figure 1.As shown in Fig. 2 Buaacache operates in Linux
Under 64 4.4 versions of stable kernel, the Block Device Driver layer being operated in Linux block device I/O architectures is registered as
Target drives (Target Driver) under Linux kernel Device Mapper frameworks, are moved in the way of kernel-driven
State loading is used.The drive module calls dmsetup programs in Device Mapper by software diskette array and Apache
Pass is one as a whole creation and mixes block device, and user can operate the equipment as reading and writing common block device.
The system structure of the present invention is as shown in figure 3, when user performs read-write requests, the request is caught by file system first
Catch, request is issued to general block device layer by file system, is specifically presented in the form of kernel data structure bio, is then proceeded to
It is handed down to Device Mapper layers, after operation is split and recombinated etc. to Device Mapper layers to bio, is finally handed down to
Buaacache drives layer.
The buffer structure of the present invention is as shown in figure 4, first cache blocks of each nonvolatile memory Apache Pass
Can be used as superblock (Super Block), the key message related for deposit whole caching also can retain to stay and use it for anything else.Tightly
Then metadata space preserves some metadata (Meta Data), and meta-data region is stored for managing data cache block (Data
Block metadata).Data field is divided into the data cache block (Data Block) of some specified sizes, gives tacit consent to per 8 sectors
One cache blocks of composition, constitute a group (Set) per 512 cache blocks, while the hard disk in software RAID is also divided by this.Often
The initial sector numbering of individual cache blocks record correspondence hard disk block, is recorded by metadata structure body, and each metadata structure body is safeguarded
Corresponding state, necessary lock and tag information.Metadata and data block are linearly deposited according to sequencing.
The caching mapping mode of the present invention is as shown in Figure 5.The present invention is connected mapping mechanism using 512 tunnel groups, it is to avoid with unit
Data are that the hyperpyrexia degrees of data of representative occurs clustering phenomena.The group mapping that is connected can be divided into directly mapping and linear Hash detects two steps
Suddenly carry out：The first step：Directly map, group disk block being mapped in buffer memory device；Second：Linear Hash detection,
Once target group is found, just in the group corresponding data block of interior linear search；Mapping be connected by group can be by local model on disk
The block of sequential data for enclosing is cached in a target group.
The caching read-write flow chart of the present invention respectively as shown in Figure 6 and Figure 7, only support to write back by cache garbage collection mechanism of the present invention
Pattern.When user writable ask miss caching when, and cache blocks it is all dirty piece without free buffer block when, cache garbage collection machine
System is write back dirty piece had not visited in nearest 20 minutes to disk array, is maintained data using Two-Handed clock algorithms
Concordance.
The present invention power loss recovery mechanism as shown in figure 8, the present invention user writable request it is miss when, once have first number
According to renewal, buffer memory device is write in time from internal memory with byte addressing system.After generation accident power-off accident, the metadata in internal memory
In buffer memory device, after main frame is re-powered, Buaacache drive modules will can be backed up in buffer memory device for backup in time
Metadata be re-loaded in internal memory, then by metadata in buffer memory device corresponding dirty data (because power-off from caching not and
When write back the data of disk array) write back to RAID, realize power loss recovery.
The present invention carries out secondary development based on scheme d m-cache of increasing income, as described in the content of the invention, by dm-cache from interior
3.10 version of core is transplanted to 4.4 long-term support version of kernel.Transplanting work is to block device read-write requests field bio and Device
Part field in Mapper carries out kernel change tracking, is accordingly adapted to.Bio is of generic block layer in linux kernel
Individual kernel data structure, is responsible for contact core buffer and block device.
As shown in figure 9, the newly-increased bvec_iter structures of bio fields compared with 3.10 version of kernel, in 4.4 version of kernel
Body, encapsulates, tetra- critical fielies of bi_size, bi_idx and bi_bvec_done.
As shown in Figure 10, Device Mapper frameworks provide synchronous or asynchronous I/O service, in kernel 4.4
Dm-io mono- has four kinds of dm_io_mem_type types.Compared with 3.10 version of kernel, in 4.4 version of kernel, dm_io_
Memory struct bio*bio substitute struct bio_vec, and dm_io_memtype substitutes DM_IO_ with DM_IO_BIO
BVEC。
Claims (2)
1. a kind of based on nonvolatile memory and the caching system of software RAID, it is characterised in that：It is characterized by a kind of fusion
Nonvolatile memory (Apache Pass), software RAID and Device Mapper drive modules (Buaacache) it is new
Caching system framework；
The nonvolatile memory is referred to not to be lost with fully powered-off rear information, and byte is addressed and I/O superior performance characteristics
New storage device, use as the caching of software RAID in caching system；
The software RAID is referred in (SuSE) Linux OS, is completed using "-C " or "-create " parameter of madam softwares
Create, be managed by mdadm；The RAID is redundancy RAID or nonredundancy RAID；
Device Mapper drive modules Buaacache are driven based on the kernel under Linux Device Mapper frameworks
Dynamic model block Buaacache, the Block Device Driver layer being operated in Linux block device I/O architectures, the kernel module is in logic
Using nonvolatile memory Apache Pass as low speed software RAID caching (Cache), physically by software RAID and non-
Volatile memory is a mixing block device as a whole creation；Buaacache drive modules include data cached group
Knit module, caching mapping block, cache garbage collection module, metadata management module and power loss recovery module；
The data cached molded tissue block is referred to and for Apache Pass to be divided into reserved area, meta-data region and data cache block area.
Reserved area is responsible for storage file system superblock or is reserved for other use, and meta-data region is responsible for storing essential record cache blocks and hard disk block
The metadata of corresponding relation, data cache block area is with cache blocks type of organization data storage；
The cache blocks mapping block refers to and the disk in Apache Pass and software RAID is divided into according to fixed size
Some groups (Set), is connected mapping mechanism using 512 tunnel groups, it is to avoid it is existing that the hyperpyrexia degrees of data with metadata as representative occurs aggregation
As；The group mapping that is connected is divided into directly mapping and linear Hash detects two steps and carries out；
The cache garbage collection module referred to using Two-Handed clock algorithms, write back Apache Pass it is nearest 20 minutes in not
Dirty piece for accessing arrives disk array；
The metadata management module to refer to and write metadata to Apache Pass from internal memory or load from Apache Pass
To internal memory, addressing system is byte addressing to metadata；When from RAID write caching or from Apache Pass write back dirty piece to
During RAID, metadata updates operation is carried out；
The power loss recovery module referred to once there is metadata updates, writes back to Apache Pass in time with byte addressing system；
After generation accident power-off accident, the metadata in internal memory is backed up in buffer memory device, after main frame is re-powered in time,
Buaacache drive modules are re-loaded to the metadata for having been backed up in buffer memory device in internal memory, then will according to metadata
In buffer memory device, corresponding dirty data writes back to disk array, realizes power loss recovery.
2. according to claim 1 based on nonvolatile memory and the caching system of software RAID, it is characterised in that：Institute
Stating Device Mapper drive modules Buaacache carries out secondary development based on scheme d m-cache of increasing income, by dm-cache from
3.10 version of kernel is transplanted to 4.4 long-term support version of kernel, and concrete transplanting step includes the 1.1st step and the 1.2nd step：
1.1st step：Increase bvec_iter structures in block device read-write requests field bio field newly, encapsulation belonged to bio originally
Middle bi_sector, tetra- critical fielies of bi_size, bi_idx and bi_bvec_done；
1.2nd step：In Device Mapper fields dm_io_memory and dm_io_memtype, struct is used respectively
Bio*bio substitutes struct bio_vec, and DM_IO_BIO substitutes DM_IO_BVEC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611106177.5A CN106528001B (en) | 2016-12-05 | 2016-12-05 | A kind of caching system based on nonvolatile memory and software RAID |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611106177.5A CN106528001B (en) | 2016-12-05 | 2016-12-05 | A kind of caching system based on nonvolatile memory and software RAID |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106528001A true CN106528001A (en) | 2017-03-22 |
| CN106528001B CN106528001B (en) | 2019-08-23 |
Family
ID=58341307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611106177.5A Active CN106528001B (en) | 2016-12-05 | 2016-12-05 | A kind of caching system based on nonvolatile memory and software RAID |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106528001B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577492A (en) * | 2017-08-10 | 2018-01-12 | 上海交通大学 | The NVM block device drives method and system of accelerating file system read-write |
| CN108108130A (en) * | 2017-12-22 | 2018-06-01 | 深圳忆联信息系统有限公司 | A kind of method and solid state disk for promoting solid state disk read-write performance |
| CN108932203A (en) * | 2017-05-29 | 2018-12-04 | 爱思开海力士有限公司 | Data processing system and data processing method |
| CN109086425A (en) * | 2018-08-09 | 2018-12-25 | 北京百度网讯科技有限公司 | Data processing method and device for database |
| CN109240609A (en) * | 2018-08-23 | 2019-01-18 | 郑州云海信息技术有限公司 | A kind of data space reading/writing method and system based on AEP memory |
| WO2019120165A1 (en) * | 2017-12-19 | 2019-06-27 | 中国科学院声学研究所 | Supported content filtering method for hybrid storage system |
| CN110032526A (en) * | 2019-04-16 | 2019-07-19 | 苏州浪潮智能科技有限公司 | A kind of caching of page method, system and equipment based on non-volatile media |
| CN110532136A (en) * | 2019-08-30 | 2019-12-03 | 四川效率源信息安全技术股份有限公司 | A kind of raid data reconstruction method based on metadata |
| CN111158599A (en) * | 2019-12-29 | 2020-05-15 | 北京浪潮数据技术有限公司 | Method, device and equipment for writing data and storage medium |
| CN112069091A (en) * | 2020-08-17 | 2020-12-11 | 北京科技大学 | Access optimization method and device applied to molecular dynamics simulation software |
| CN113326072A (en) * | 2021-05-24 | 2021-08-31 | 北京计算机技术及应用研究所 | Real-time monitoring method based on nonvolatile memory under Feiteng server platform |
| CN114201115A (en) * | 2021-12-14 | 2022-03-18 | 北京达佳互联信息技术有限公司 | Data storage system, method, computer device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1527973A (en) * | 2000-06-23 | 2004-09-08 | 英特尔公司 | Non-volatile cache |
| CN101236526A (en) * | 2007-01-30 | 2008-08-06 | 扬智科技股份有限公司 | Computer system having cache system directly connected to nonvolatile storage device |
| US20090049261A1 (en) * | 2007-08-15 | 2009-02-19 | Raymond Duchesne | Method to accelerate block level snapshots in archiving storage systems |
| CN102043731A (en) * | 2010-12-17 | 2011-05-04 | 天津曙光计算机产业有限公司 | Cache system of storage system |
| CN102053929A (en) * | 2010-12-17 | 2011-05-11 | 天津曙光计算机产业有限公司 | IO cache operation method and system based on DM layer of Linux system |
| CN102147802A (en) * | 2010-12-17 | 2011-08-10 | 曙光信息产业(北京)有限公司 | Pseudo-random type NFS application acceleration system |
| CN102203751A (en) * | 2008-10-30 | 2011-09-28 | 惠普开发有限公司 | Redundant array of independent disks (raid) write cache sub-assembly |
| CN102521147A (en) * | 2011-11-17 | 2012-06-27 | 曙光信息产业(北京)有限公司 | Management method by using rapid non-volatile medium as cache |
| CN104035887A (en) * | 2014-05-22 | 2014-09-10 | 中国科学院计算技术研究所 | Block device caching device and method based on simplification configuration system |
| CN104679442A (en) * | 2013-12-02 | 2015-06-03 | 中兴通讯股份有限公司 | Method and device for improving performance of disk array |
| CN105339885A (en) * | 2013-05-23 | 2016-02-17 | 网络装置公司 | Efficient storage of small random changes to data on disk |
| CN105955841A (en) * | 2016-04-18 | 2016-09-21 | 华中科技大学 | Method for RAID dual-controller to write cache mirror with disk |
-
2016
- 2016-12-05 CN CN201611106177.5A patent/CN106528001B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1527973A (en) * | 2000-06-23 | 2004-09-08 | 英特尔公司 | Non-volatile cache |
| CN101236526A (en) * | 2007-01-30 | 2008-08-06 | 扬智科技股份有限公司 | Computer system having cache system directly connected to nonvolatile storage device |
| US20090049261A1 (en) * | 2007-08-15 | 2009-02-19 | Raymond Duchesne | Method to accelerate block level snapshots in archiving storage systems |
| CN102203751A (en) * | 2008-10-30 | 2011-09-28 | 惠普开发有限公司 | Redundant array of independent disks (raid) write cache sub-assembly |
| CN102043731A (en) * | 2010-12-17 | 2011-05-04 | 天津曙光计算机产业有限公司 | Cache system of storage system |
| CN102053929A (en) * | 2010-12-17 | 2011-05-11 | 天津曙光计算机产业有限公司 | IO cache operation method and system based on DM layer of Linux system |
| CN102147802A (en) * | 2010-12-17 | 2011-08-10 | 曙光信息产业(北京)有限公司 | Pseudo-random type NFS application acceleration system |
| CN102521147A (en) * | 2011-11-17 | 2012-06-27 | 曙光信息产业(北京)有限公司 | Management method by using rapid non-volatile medium as cache |
| CN105339885A (en) * | 2013-05-23 | 2016-02-17 | 网络装置公司 | Efficient storage of small random changes to data on disk |
| CN104679442A (en) * | 2013-12-02 | 2015-06-03 | 中兴通讯股份有限公司 | Method and device for improving performance of disk array |
| CN104035887A (en) * | 2014-05-22 | 2014-09-10 | 中国科学院计算技术研究所 | Block device caching device and method based on simplification configuration system |
| CN105955841A (en) * | 2016-04-18 | 2016-09-21 | 华中科技大学 | Method for RAID dual-controller to write cache mirror with disk |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932203A (en) * | 2017-05-29 | 2018-12-04 | 爱思开海力士有限公司 | Data processing system and data processing method |
| CN107577492A (en) * | 2017-08-10 | 2018-01-12 | 上海交通大学 | The NVM block device drives method and system of accelerating file system read-write |
| WO2019120165A1 (en) * | 2017-12-19 | 2019-06-27 | 中国科学院声学研究所 | Supported content filtering method for hybrid storage system |
| CN108108130A (en) * | 2017-12-22 | 2018-06-01 | 深圳忆联信息系统有限公司 | A kind of method and solid state disk for promoting solid state disk read-write performance |
| CN109086425A (en) * | 2018-08-09 | 2018-12-25 | 北京百度网讯科技有限公司 | Data processing method and device for database |
| CN109086425B (en) * | 2018-08-09 | 2022-05-06 | 北京百度网讯科技有限公司 | Data processing method and device for database |
| CN109240609B (en) * | 2018-08-23 | 2022-02-18 | 郑州云海信息技术有限公司 | Data space read-write method and system based on AEP memory |
| CN109240609A (en) * | 2018-08-23 | 2019-01-18 | 郑州云海信息技术有限公司 | A kind of data space reading/writing method and system based on AEP memory |
| CN110032526B (en) * | 2019-04-16 | 2021-10-15 | 苏州浪潮智能科技有限公司 | Page caching method, system and equipment based on nonvolatile medium |
| CN110032526A (en) * | 2019-04-16 | 2019-07-19 | 苏州浪潮智能科技有限公司 | A kind of caching of page method, system and equipment based on non-volatile media |
| CN110532136A (en) * | 2019-08-30 | 2019-12-03 | 四川效率源信息安全技术股份有限公司 | A kind of raid data reconstruction method based on metadata |
| CN110532136B (en) * | 2019-08-30 | 2023-05-02 | 四川效率源信息安全技术股份有限公司 | Raid data recovery method based on metadata |
| CN111158599A (en) * | 2019-12-29 | 2020-05-15 | 北京浪潮数据技术有限公司 | Method, device and equipment for writing data and storage medium |
| CN111158599B (en) * | 2019-12-29 | 2022-03-22 | 北京浪潮数据技术有限公司 | Method, device and equipment for writing data and storage medium |
| CN112069091A (en) * | 2020-08-17 | 2020-12-11 | 北京科技大学 | Access optimization method and device applied to molecular dynamics simulation software |
| CN112069091B (en) * | 2020-08-17 | 2023-09-01 | 北京科技大学 | Memory access optimization method and device applied to molecular dynamics simulation software |
| CN113326072A (en) * | 2021-05-24 | 2021-08-31 | 北京计算机技术及应用研究所 | Real-time monitoring method based on nonvolatile memory under Feiteng server platform |
| CN113326072B (en) * | 2021-05-24 | 2023-11-24 | 北京计算机技术及应用研究所 | Real-time monitoring method based on nonvolatile memory under Feiteng server platform |
| CN114201115A (en) * | 2021-12-14 | 2022-03-18 | 北京达佳互联信息技术有限公司 | Data storage system, method, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106528001B (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106528001B (en) | A kind of caching system based on nonvolatile memory and software RAID | |
| US10289544B2 (en) | Mapping tables for storage devices | |
| US8725946B2 (en) | Mass storage system and method of using hard disk, solid-state media, PCIe edge connector, and raid controller | |
| JP6007329B2 (en) | Storage controller, storage device, storage system | |
| US10509776B2 (en) | Time sequence data management | |
| CN103530237B (en) | A kind of rubbish recovering method of Solid-state disc array | |
| JP6732684B2 (en) | Information processing device, storage device, and information processing system | |
| US20140047166A1 (en) | Storage system employing mram and array of solid state disks with integrated switch | |
| CN109344090B (en) | Virtual hard disk system of KVM virtual machine in data center and data center | |
| CN102508724B (en) | Disk bad block processing method based on soft RAID (redundant array of independent disks) | |
| US9075754B1 (en) | Managing cache backup and restore | |
| CN107301016A (en) | Validity for refuse collection is tracked | |
| US9021222B1 (en) | Managing incremental cache backup and restore | |
| US10956071B2 (en) | Container key value store for data storage devices | |
| Deng et al. | Architectures and optimization methods of flash memory based storage systems | |
| CN104572478A (en) | Data access method and data access device | |
| TW201028843A (en) | Method and system for dynamic storage tiering using allocate-on-write snapshots | |
| CN101604226A (en) | A kind of method that makes up raising performance of storage system in dynamic buffering pond based on virtual RAID | |
| CN102521147A (en) | Management method by using rapid non-volatile medium as cache | |
| Myers | On the use of NAND flash memory in high-performance relational databases | |
| CN109144899A (en) | Method for managing table recovery | |
| CN109739696B (en) | Double-control storage array solid state disk caching acceleration method | |
| CN101414244A (en) | A kind of methods, devices and systems of processing data under network environment | |
| US10031689B2 (en) | Stream management for storage devices | |
| Lee | High-performance NAND and PRAM hybrid storage design for consumer electronics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |