CN111324306B - Data classification cache allocation method based on NVDIMM - Google Patents
Data classification cache allocation method based on NVDIMM Download PDFInfo
- Publication number
- CN111324306B CN111324306B CN202010094577.9A CN202010094577A CN111324306B CN 111324306 B CN111324306 B CN 111324306B CN 202010094577 A CN202010094577 A CN 202010094577A CN 111324306 B CN111324306 B CN 111324306B
- Authority
- CN
- China
- Prior art keywords
- nvdimm
- data
- metadata
- space
- region
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000000872 buffer Substances 0.000 claims abstract description 26
- 238000011084 recovery Methods 0.000 claims description 10
- 238000013524 data verification Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 4
- 230000003321 amplification Effects 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019580 granularity Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
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
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1415—Saving, restoring, recovering or retrying at system level
- G06F11/1438—Restarting or rejuvenating
-
- 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
- G06F3/0629—Configuration or reconfiguration of storage systems
- G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
-
- G—PHYSICS
- G06—COMPUTING; 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
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Abstract
The invention discloses a data classification cache allocation method based on an NVDIMM (non-volatile memory Module). NVDIMM equipment is mapped to a memory address space to obtain an NVDIMM data space; according to various data requirements of application, dividing the NVDIMM data space into a unique NVDIMM metadata area and one or more NVDIMM data cache areas from logic; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata area and the NVDIMM data buffer area are independent from each other and do not overlap each other in the NVDIMM data space. And caching the data in the corresponding NVDIMM data cache region according to the user requirement. The method realizes data classification caching and management of the NVDIMM, and simultaneously stores management metadata and managed data on the NVDIMM medium.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the technical field of data storage, and particularly relates to a data classification cache allocation method based on an NVDIMM.
[ background of the invention ]
With the advent of the big data era, the business application has an increasing demand on the storage space of data and an increasing demand on the read-write efficiency. On the other hand, due to the large amount of repeated data caused by the large amount of copying, backup and repeated reference, the need for deleting the repeated data is increasing, and therefore, compared with the traditional access method based on the storage address, in the new generation of distributed storage system, the access method based on the content is widely used to implement the repeated data deletion based on the content.
Thanks to the rapid development and popularization of SSDs (solid state disks), SSDs (solid state disks) are largely used as storage media in the new generation of distributed storage. The SSD has no addressing process, so that the access efficiency, particularly the random access efficiency, can be effectively improved. However, due to the hardware characteristics of the SSD, the actual written data on the SSD is far more than the written data written by a user, which brings obvious problems of write amplification and the like; and when the use capacity of the SSD exceeds a threshold value, the garbage recovery greatly influences the performance of the SSD. In addition, SSD read and write speeds have a significant gap relative to DRAMs. Therefore, NVDIMMs that combine the non-volatile features of SSDs with high speed access of DRAMs are becoming more expensive in the storage area.
In the existing mainstream distributed storage field, a DRAM (dynamic random access memory) is mostly used as an operating memory, and an SSD is used as a back-end storage or a cache. When a system is designed, problems such as SSD write amplification, data persistence and data reloading and recovery after system restart are considered comprehensively, and a plurality of limitations are generated in the aspect of system design.
[ summary of the invention ]
The invention aims to provide a data classification cache allocation method based on an NVDIMM (noise, vibration and memory Module), which realizes data classification caching and management of the NVDIMM and simultaneously stores management metadata and managed data on an NVDIMM medium.
The invention adopts the following technical scheme: a data classification cache allocation method based on NVDIMM comprises the following steps:
mapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space; according to various data requirements of application, dividing the NVDIMM data space into a unique NVDIMM metadata area and one or more NVDIMM data cache areas from logic; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata area and the NVDIMM data buffer area are independent from each other and do not overlap each other in the NVDIMM data space.
And caching the data in the corresponding NVDIMM data cache region according to the user requirement.
Further, the method also includes the following steps: when the usage rate of the NVDIMM data cache region reaches a set level or is full, the existing NVDIMM data cache region is partially or completely written back to the SSD by adopting an exit mechanism.
Further, the method also includes the following steps: when the NVDIMM data cache area is stopped from being used, the existing NVDIMM data cache area data is partially or completely written back to the SSD.
Further, the method also includes the following steps: when the system where the NVDIMMN is located stops working unexpectedly, the data recovery process of the VDIMM data cache region is as follows:
remapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space;
carrying out information verification on the NVDIMM metadata area to ensure the integrity of the NVDIMM metadata area;
analyzing the information of the NVDIMM data cache region partition table to obtain the initial offset and the capacity of each NVDIMM data cache region; comparing the current base address of the NVDIMM data space with the previous base address of the NVDIMM data space to obtain correct initial address information of each NVDIMM data cache region;
respectively carrying out data verification, replay and write-back SSD on each NVDIMM data cache region; the NVDIMM metadata region update flag indicates completion of the exception recovery after completion.
Further, the NVDIMM metadata region is partitioned from the NVDIMM data space starting address; the NVDIMM data cache region is divided in the NVDIMM data space in sequence next to the NVDIMM metadata region.
Further, the NVDIMM data cache region comprises a fixed-length NVDIMM data cache region and a variable-length NVDIMM data cache region; the fixed-length NVDIMM data cache region is used for caching data with fixed and unchangeable occupied size of the data space, and the variable-length NVDIMM data cache region is used for caching data with possibly changeable occupied size of the data space.
Further, the fixed-length NVDIMM data buffer area space is managed and accessed in an array form.
Furthermore, in a data cache region of the variable-length NVDIMM, variable-length data are managed by adopting variable-length data load and variable-length data metadata; the variable length data metadata comprises a variable length data start offset and a variable length data load length; the variable-length data loads are sequentially stored from one side of the NVDIMM data cache region and are not overlapped; the variable-length data metadata are stored from the other side of the NVDIMM data cache region to the variable-length data load side and are not overlapped; the variable length data payload and variable length data metadata are close together in space usage to the middle of the variable length NVDIMM data cache region.
Further, the NVDIMM metadata region at least includes the following units:
NVDIMM metadata region version number: for identifying NVDIMM metadata region version number;
NVDIMM data space current base address: for saving the currently validated NVDIMM data space starting address;
NVDIMM data space front base address: the method is used for saving the current base address of the data space of the NVDIMM when the NVDIMM is withdrawn last time, and is used for recovering from accidental withdrawal;
NVDIMM normal off flag: the device is used for indicating whether NVDIMM metadata area verification and NVDIMM data cache area data verification, replay and write-back SSD are needed or not;
NVDIMM data cache area information partition table: the data cache region information of each NVDIMM is recorded and managed;
NVDIMM metadata region checksum: for NVDIMM metadata region data integrity checking.
The invention also discloses the NVDIMM in the data classification cache allocation method based on the NVDIMM, wherein the data space of the NVDIMM is logically divided into a unique NVDIMM metadata area and one or more NVDIMM data cache areas; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata area and the NVDIMM data buffer area are independent from each other and do not overlap each other in the NVDIMM data space.
The invention has the beneficial effects that: 1. and carrying out custom memory management on the NVDIMM. 2. The NVDIMM is partitioned into different segments, pre-allocated for use with different types of data. 3. The partitioning scheme is directly stored in the NVDIMM metadata space, and the metadata is subjected to check protection. 4. High-speed random access memory, minimizing IO access time. 5. The method is suitable for data access and cache with different granularities, and the problems of write amplification and SSD service life are not needed to be worried about. 6. When unexpected power failure, system crash and unexpected restart occur, rapid data recovery can be realized without additional storage media.
[ description of the drawings ]
Fig. 1 is a schematic diagram of NVDIMM data space pre-allocation.
Fig. 2 is a diagram illustrating a data classification cache metadata region of the NVDIMM.
Fig. 3 is a schematic diagram of a fixed-length data buffer of an NVDIMM.
Fig. 4 is a schematic diagram of an NVDIMM variable length data buffer.
Fig. 5 is a NVDIMM initialization flow diagram.
Fig. 6 is a flow diagram of NVDIMM data classification cache opening.
Fig. 7 is a flow chart of NVDIMM data classification cache shutdown.
FIG. 8 is a flow diagram of NVDIMM data classification cache error recovery.
[ detailed description ] embodiments
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention discloses a data classification cache allocation method based on NVDIMM, which comprises the following steps: mapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space; according to various data requirements of application, such as data types, data cold and hot degrees and the like, dividing the NVDIMM data space into a unique NVDIMM metadata area and one or more NVDIMM data cache areas from logic; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata region and the NVDIMM data buffer regions are independent from each other and do not overlap each other in the NVDIMM data space. And caching the data in the corresponding NVDIMM data cache region according to the user requirement.
The NVDIMM metadata area is used for storing important information of the NVDIMM equipment and each NVDIMM data cache area, and the important information is used for normal loading, unloading and recovering of the NVDIMM equipment. The NVDIMM data cache region is responsible for allocating, caching, and managing the same data type. Different NVDIMM data buffers may manage different or the same data types. The capacity, the purpose and the dynamic setting of each NVDIMM data buffer area can be realized.
The method further comprises the following steps: and when the usage rate of the NVDIMM data cache region reaches a set degree or is full, partially or completely writing back the data of the existing NVDIMM data cache region to the SSD by adopting an exit mechanism. The access speed is improved, the SSD is prevented from being rewritten, and the service life of the SSD is prolonged.
The method further comprises the following steps: when the NVDIMM data cache area is stopped from being used, the existing NVDIMM data cache area data is partially or completely written back to the SSD.
The method further comprises the following steps: when the system where the NVDIMMN is located unexpectedly stops working, the VDIMM data buffer data recovery process is as follows, as shown in fig. 8:
remapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space;
carrying out information verification on the NVDIMM metadata area to ensure the integrity of the NVDIMM metadata area;
analyzing the information of the NVDIMM data cache region partition table to obtain the initial offset and the capacity of each NVDIMM data cache region; comparing the current base address of the NVDIMM data space with the previous base address of the NVDIMM data space to obtain correct initial address information of each NVDIMM data cache region;
respectively carrying out data verification, replay and write-back SSD on each NVDIMM data cache region; the NVDIMM metadata region update flag indicates completion of the exception recovery after completion.
The NVDIMM metadata region is partitioned from the NVDIMM data space starting address; the NVDIMM data cache region is divided in the NVDIMM data space in sequence next to the NVDIMM metadata region.
The NVDIMM data cache region comprises a fixed-length NVDIMM data cache region and a variable-length NVDIMM data cache region; the fixed-length NVDIMM data cache region is used for caching data with fixed and unchangeable occupied size of the data space, and the variable-length NVDIMM data cache region is used for caching data with possibly changeable occupied size of the data space. The variable length data payload and variable length data metadata are close together in space usage to the middle of the variable length NVDIMM data cache region. As shown in fig. 3, the data buffer 2 is set as a plurality of fixed-length data buffers, namely, fixed-length data 1 and fixed-length data 2 … …, namely, fixed-length data N. The fixed-length NVDIMM data cache region space is managed and accessed in an array form.
As shown in fig. 4, the data buffer 2 is also shown, which does not refer to the data buffer 2 in fig. 3 that has been set to fixed-length data, but only shows a diagram. As shown in fig. 4, the data buffer 2 is set as a variable-length data buffer. In a data cache region of the variable-length NVDIMM, variable-length data are managed by adopting variable-length data load and variable-length data metadata; the variable length data metadata comprises a variable length data start offset and a variable length data load length; the variable-length data loads are sequentially stored from one side of the NVDIMM data cache region and are not overlapped; the variable-length data metadata are stored from the other side of the NVDIMM data cache region to the variable-length data load side and are not overlapped; the variable length data payload and variable length data metadata are close together in space usage to the middle of the variable length NVDIMM data cache region.
As shown in fig. 1, the data buffer areas are a data buffer area 1 and a data buffer area 2 … …, respectively, and a data buffer area N.
As shown in fig. 2: the NVDIMM metadata region at least includes the following units:
NVDIMM metadata region version number: for identifying NVDIMM metadata region version number;
NVDIMM data space current base address: for saving the currently validated NVDIMM data space starting address;
NVDIMM data space front base address: the method is used for saving the current base address of the data space of the NVDIMM when the NVDIMM is withdrawn last time, and is used for recovering from accidental withdrawal;
NVDIMM normal off flag: the device is used for indicating whether NVDIMM metadata area verification and NVDIMM data cache area data verification, replay and write-back SSD are needed or not;
NVDIMM data cache area information partition table: the data cache region information of each NVDIMM is recorded and managed;
NVDIMM metadata region checksum: for NVDIMM metadata region data integrity checking.
In the above NVDIMM in the data classification cache allocation method based on NVDIMM, the NVDIMM data space is logically divided into a unique NVDIMM metadata region and one or more NVDIMM data cache regions; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata region and the NVDIMM data buffer regions are independent from each other and do not overlap each other in the NVDIMM data space.
The NVDIMM is used as follows: as shown in fig. 5, the NVDIMM device is discovered, and is mapped to the memory address space, the NVDIMM space is initialized in segments according to the application requirements, the NVDIMM metadata area is updated, and the data classification buffer area is notified that the user starts to use the data classification buffer area.
As shown in fig. 6, the base address of the NVDIMM is obtained by mapping the NVDIMM to the memory address space through an interface provided by the hardware vendor. And according to various types of data needing to be persisted and the size of the space occupied by the various types of data, using the storage space on the NVDIMM.
Each cache user initializes or uses a respective data cache region to perform custom memory management.
And informing each cache user to stop using the data cache region and preparing for closing. After each cache user stops using the data cache region, the NVDIMM metadata region is updated and verified, and the NVDIMM content is refreshed to the NVDIMM back-end storage, as shown in FIG. 7.
Claims (3)
1. A data classification cache allocation method based on NVDIMM is characterized by comprising the following steps:
mapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space; according to various data requirements of application, dividing the NVDIMM data space into a unique NVDIMM metadata area and one or more NVDIMM data cache areas from logic; the NVDIMM metadata area and each NVDIMM data buffer area are independent from each other and do not overlap with each other in the NVDIMM data space;
caching data in each corresponding NVDIMM data cache region;
the method further comprises the following steps: when the usage rate of the NVDIMM data cache region reaches a set degree or is full, adopting an exit mechanism to write back part or all of the data of the existing NVDIMM data cache region to the SSD;
when the system where the NVDIMM is located stops working unexpectedly, the data recovery process of the NVDIMM data buffer area is as follows:
remapping the NVDIMM equipment to a memory address space to obtain an NVDIMM data space;
carrying out information verification on the NVDIMM metadata area to ensure the integrity of the NVDIMM metadata area;
analyzing the information of the NVDIMM data cache region partition table to obtain the initial offset and the capacity of each NVDIMM data cache region; comparing the current base address of the NVDIMM data space with the previous base address of the NVDIMM data space to obtain correct initial address information of each NVDIMM data cache region; to pair
Each NVDIMM data cache area respectively performs data verification, replay and write-back SSD; after completion, the NVDIMM metadata area update identification indicates that the abnormal recovery is completed;
the method further comprises the following steps: when the NVDIMM data cache region is stopped to be used, the existing NVDIMM data cache region data is partially or completely written back to the SSD;
the NVDIMM metadata region is partitioned from an NVDIMM data space starting address; the NVDIMM data cache region is sequentially divided in an NVDIMM data space next to the NVDIMM metadata region;
the NVDIMM data cache region comprises a fixed-length NVDIMM data cache region and a variable-length NVDIMM data cache region; the fixed-length NVDIMM data cache region is used for caching data with fixed and unchangeable occupied size of a data space, and the variable-length NVDIMM data cache region is used for caching data with possibly changeable occupied size of the data space;
the fixed-length NVDIMM data cache region space is managed and accessed in an array form;
in the data cache region of the variable-length NVDIMM, data are managed by data load and data metadata; the data metadata comprises a data start offset and a variable length data load length; the data loads are stored in sequence from one side of the NVDIMM data cache region and are not overlapped; the data metadata are stored from the other side of the NVDIMM data cache region to the data load side and are not overlapped; the data payload and data metadata are close together in space usage towards the middle of the variable length NVDIMM data cache region.
2. The method according to claim 1, wherein the NVDIMM metadata section at least comprises the following units:
NVDIMM metadata region version number: for identifying NVDIMM metadata region version number;
NVDIMM data space current base address: for saving the currently validated NVDIMM data space starting address;
NVDIMM data space front base address: the method is used for saving the current base address of the data space of the NVDIMM when the NVDIMM is withdrawn last time, and is used for recovering from accidental withdrawal;
NVDIMM normal off flag: the device is used for indicating whether NVDIMM metadata area verification and NVDIMM data cache area data verification, replay and write-back SSD are needed or not;
NVDIMM data cache area information partition table: the data cache region information of each NVDIMM is recorded and managed;
NVDIMM metadata region checksum: for NVDIMM metadata region data integrity checking.
3. An NVDIMM in an NVDIMM based data classification cache allocation method of any of claims 1-2, wherein the NVDIMM data space is logically divided into a unique NVDIMM metadata region and one or more NVDIMM data cache regions; the space size of the NVDIMM metadata area and one or more NVDIMM data cache areas is set according to the requirement of a user; the NVDIMM metadata region and the NVDIMM data buffer regions are independent from each other and do not overlap each other in the NVDIMM data space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010094577.9A CN111324306B (en) | 2020-02-16 | 2020-02-16 | Data classification cache allocation method based on NVDIMM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010094577.9A CN111324306B (en) | 2020-02-16 | 2020-02-16 | Data classification cache allocation method based on NVDIMM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111324306A CN111324306A (en) | 2020-06-23 |
| CN111324306B true CN111324306B (en) | 2021-04-20 |
Family
ID=71167107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010094577.9A Active CN111324306B (en) | 2020-02-16 | 2020-02-16 | Data classification cache allocation method based on NVDIMM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111324306B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10289340B2 (en) * | 2016-02-23 | 2019-05-14 | Sandisk Technologies Llc | Coalescing metadata and data writes via write serialization with device-level address remapping |
| US10489301B1 (en) * | 2017-04-10 | 2019-11-26 | EMC IP Holding Company LLC | Method and system for metadata churn absorption |
| US11175853B2 (en) * | 2017-05-09 | 2021-11-16 | Samsung Electronics Co., Ltd. | Systems and methods for write and flush support in hybrid memory |
| US11138121B2 (en) * | 2017-11-20 | 2021-10-05 | Samsung Electronics Co., Ltd. | Systems and methods for efficient cacheline handling based on predictions |
| CN110058964B (en) * | 2018-01-18 | 2023-05-02 | 伊姆西Ip控股有限责任公司 | Data recovery method, data recovery system, and computer readable medium |
| US10846183B2 (en) * | 2018-06-11 | 2020-11-24 | Dell Products, L.P. | Method and apparatus for ensuring data integrity in a storage cluster with the use of NVDIMM |
| CN109117088B (en) * | 2018-07-24 | 2021-02-19 | 联想(北京)有限公司 | Data processing method and system |
| CN109582508B (en) * | 2018-12-29 | 2023-12-26 | 西安紫光国芯半导体股份有限公司 | Data backup and recovery method for NVDIMM, NVDIMM controller and NVDIMM |
| CN109582507B (en) * | 2018-12-29 | 2023-12-26 | 西安紫光国芯半导体股份有限公司 | Data backup and recovery method for NVDIMM, NVDIMM controller and NVDIMM |
-
2020
- 2020-02-16 CN CN202010094577.9A patent/CN111324306B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111324306A (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5619423B2 (en) | Hybrid solid-state memory system with volatile and non-volatile memory | |
| US20050015557A1 (en) | Nonvolatile memory unit with specific cache | |
| CN111475427A (en) | Logical-to-physical mapping management using low latency nonvolatile memory | |
| US7613870B2 (en) | Efficient memory usage in systems including volatile and high-density memories | |
| CN105718530B (en) | File storage system and file storage control method thereof | |
| US20140122774A1 (en) | Method for Managing Data of Solid State Storage with Data Attributes | |
| US8341336B2 (en) | Region-based management method of non-volatile memory | |
| US9524238B2 (en) | Systems and methods for managing cache of a data storage device | |
| US20030005219A1 (en) | Partitioning cache metadata state | |
| US8429339B2 (en) | Storage device utilizing free pages in compressed blocks | |
| US11954031B2 (en) | Enhancing cache dirty information | |
| CN107861884B (en) | Method for improving cross-page memory address mapping efficiency in NAND flash memory | |
| US11334480B2 (en) | Data storage device and non-volatile memory control method | |
| CN101192195B (en) | Packet management method for electronic hard disk memory space | |
| KR20070031647A (en) | Space-Efficient Management Method of Compressed Data in Flash Memory Storages | |
| CN111324306B (en) | Data classification cache allocation method based on NVDIMM | |
| KR102589609B1 (en) | Snapshot management in partitioned storage | |
| CN110309081A (en) | The method of FTL read-write data page based on compression storage and address of cache list item | |
| CN108733575B (en) | Method for reconstructing physical mapping table by logic after power-off restart and solid state disk | |
| CN111949212B (en) | File system and file management method based on self-defined open channel SSD | |
| CN112035065B (en) | Data writing method, device and equipment and computer readable storage medium | |
| US11853563B1 (en) | Key value data storage device with tiers | |
| CN117827082A (en) | Data storage system | |
| CN114238175A (en) | Solid state disk FTL algorithm address mapping method | |
| CN117950590A (en) | Method for optimizing ZenFS reset operation to prolong service life of ZNS-SSD |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method of Data Classification Cache Allocation Based on NVDIMM Effective date of registration: 20230111 Granted publication date: 20210420 Pledgee: Shaanxi Xixian New Area Small Loan Co.,Ltd. Pledgor: Xi'an Okayun Data Technology Co.,Ltd. Registration number: Y2023610000033 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230710 Granted publication date: 20210420 Pledgee: Shaanxi Xixian New Area Small Loan Co.,Ltd. Pledgor: Xi'an Okayun Data Technology Co.,Ltd. Registration number: Y2023610000033 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Data Classification Cache Allocation Method Based on NVDIMM Effective date of registration: 20230712 Granted publication date: 20210420 Pledgee: Shaanxi Xixian New Area Small Loan Co.,Ltd. Pledgor: Xi'an Okayun Data Technology Co.,Ltd. Registration number: Y2023610000562 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20231219 Granted publication date: 20210420 Pledgee: Shaanxi Xixian New Area Small Loan Co.,Ltd. Pledgor: Xi'an Okayun Data Technology Co.,Ltd. Registration number: Y2023610000562 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Data Classification Cache Allocation Method Based on NVDIMM Effective date of registration: 20231228 Granted publication date: 20210420 Pledgee: Shaanxi Xixian New Area Small Loan Co.,Ltd. Pledgor: Xi'an Okayun Data Technology Co.,Ltd. Registration number: Y2023980075147 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |