CN118092813B - Reserved space adjusting method for NAND product - Google Patents
Reserved space adjusting method for NAND product Download PDFInfo
- Publication number
- CN118092813B CN118092813B CN202410481719.5A CN202410481719A CN118092813B CN 118092813 B CN118092813 B CN 118092813B CN 202410481719 A CN202410481719 A CN 202410481719A CN 118092813 B CN118092813 B CN 118092813B
- Authority
- CN
- China
- Prior art keywords
- nand
- value
- database
- performance
- test
- 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 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 24
- 230000003321 amplification Effects 0.000 claims description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 5
- 238000011056 performance test Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 abstract description 2
- 238000011002 quantification Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000004513 sizing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a reserved space adjusting method for NAND products, which comprises the steps of establishing an OP database, storing OP values corresponding to different NAND products in different use scenes and user demands, and further rapidly acquiring the corresponding OP values by inquiring the OP database after determining the product demands, so as to finish the adjustment and optimization of the NAND; the OP database is also used for training the artificial neural network model to obtain an OP prediction model, so that when the corresponding OP value cannot be queried in the OP database, the training model can be used for obtaining the corresponding OP value, and further, the NAND is optimized and the OP database is updated, and the purposes of optimizing the performance, the service life, the cost and the system stability of the solid state disk are achieved.
Description
Technical Field
The invention relates to the technical field related to NAND firmware testing, in particular to a reserved space adjusting method for NAND products.
Background
The reserved space OP (Over-division) size has a significant impact on the performance and durability (lifetime) of the solid state disk NAND, with major impact aspects: 1. performance stability; 2. write amplification and endurance (lifetime); 3. space available to the user (cost); 4. wear balance and garbage recycling efficiency.
The OP of the NAND product is generally a fixed value and cannot be adjusted, and a proper OP value cannot be set according to different use scenes and user requirements, so that the performance, service life, cost and system stability of the solid state disk are all affected.
In view of the above-mentioned drawbacks, there is a need to design a headspace adjustment method for NAND products to overcome the above-mentioned drawbacks of the prior art.
Disclosure of Invention
In order to solve the problems mentioned in the above, the invention provides a method for adjusting the reserved space of a NAND product, so as to set a proper OP value according to different use scenes and user requirements, and achieve the purposes of optimizing the performance, service life, cost and system stability of the solid state disk.
A headspace adjustment method for a NAND product, characterized by: the method comprises the following steps:
Step 1, determining the NAND requirement;
Step 2, evaluating the current OP value of the NAND;
Step 3, according to the requirement in the step 1, inquiring a corresponding OP value in an OP database; if the OP value exists, the OP value of the NAND is adjusted to be the corresponding OP value, otherwise, the corresponding OP value is obtained through a prediction model, and then the OP value of the NAND is adjusted to be the corresponding OP value;
And step 4, testing and verifying whether the NAND meets the requirements in the step 1 through the OP test quantification tool set, if so, updating the OP database, otherwise, repeating the steps 3 to 4 until the requirements in the step 1 are met.
Further, in the step 1, the NAND requirements include: performance requirements, cost requirements, lifetime requirements, and system stability requirements.
Further, in the step 2, the evaluation is performed by an OP management tool.
Further, the OP management tool is configured to obtain the OP information of the NAND and adjust the OP value, where the OP information includes: current OP setting and OP adjustable range.
Further, the OP test quantization tool set is used for performance testing, wear balance testing, garbage collection and user model testing.
Further, the step of establishing the OP database is as follows:
a. Archiving test results, including: obtaining a trend graph of OP size to performance; obtaining a trend graph of OP size to NAND service life; obtaining a trend chart of OP size to garbage recovery efficiency; obtaining TBW (Total Bytes Written) data trend graphs of the OP size under a specific user model;
b. establishing a database of quantitative relations between OP and performance, WA (Write Amplification), EC (Erasure Coding), WL (Wear Leveling) efficiency, GC (Garbage Collection) efficiency and TBW under different use scenes;
c. Repeating steps a and b to refine the data for different NAND products.
Further, the prediction model is used for predicting the recommended OP setting value through the artificial neural network model; the OP database is used for training an artificial neural network model.
The beneficial effects of the invention are as follows:
1. according to the method, the OP database is established firstly, the OP values corresponding to different NAND products in different use scenes and user demands are stored, and then after the product demands are determined, the corresponding OP values can be obtained quickly by inquiring the OP database, the NAND is optimized, and the purposes of optimizing the performance, the service life, the cost and the system stability of the solid state disk are achieved.
2. The OP database is also used for training the artificial neural network model to obtain the OP prediction model, so that when the corresponding OP value cannot be queried in the OP database, the training model can be used for acquiring the corresponding OP value, and further, the NAND is regulated and the OP database is updated.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the invention.
Fig. 2 is a schematic diagram of a system architecture according to an embodiment of the invention.
Detailed Description
The invention is further described below with reference to examples.
The following examples are illustrative of the present invention but are not intended to limit the scope of the invention. The conditions in the examples can be further adjusted according to specific conditions, and simple modifications of the method of the invention under the premise of the conception of the invention are all within the scope of the invention as claimed.
As shown in fig. 1, an embodiment of a headspace adjustment method for a NAND product, the method comprising the steps of:
step 1, determining the NAND requirement; the requirements of NAND include: performance requirements, cost requirements, lifetime requirements, and system stability requirements.
Step 2, evaluating the current OP value of the NAND; the evaluation is performed by OP management tools.
Step 3, according to the requirement in the step 1, inquiring a corresponding OP value in an OP database; if the OP value exists, the OP value of the NAND is adjusted to be the corresponding OP value, otherwise, the corresponding OP value is obtained through a prediction model, and then the OP value of the NAND is adjusted to be the corresponding OP value;
And step 4, testing and verifying whether the NAND meets the requirements in the step 1 through the OP test quantification tool set, if so, updating the OP database, otherwise, repeating the steps 3 to 4 until the requirements in the step 1 are met.
Fig. 2 shows an embodiment of a system architecture according to the method of the present invention.
The OP management tool is configured to obtain OP information of NAND and adjust an OP value, where the OP information includes: current OP setting and OP adjustable range.
The OP test quantification tool set is used for performance test, wear balance test, garbage collection and user model test. (1) The performance test is used for obtaining the influence on performance after the OP adjustment, and the SNIA performance test specification can also define a performance test case; (2) The wear balance test is used for obtaining the influence on WL after OP adjustment, and generally checking the erase count dispersion and the total EC of all super blocks through a large number of reads and writes; (3) The garbage recovery is used for acquiring the influence on the GC efficiency after the OP adjustment, triggering the GC by randomly and repeatedly writing a large number of full disks, and the stability of the observation performance and the write amplification coefficient are used as main measurement indexes; (4) The user model test is used for obtaining performance and stability performance (TBW data is obtained, namely life prediction) of different user models after OP adjustment, and obtaining information such as command sequences, queue depth, configuration and the like used by a user in daily life through trace log and other means, so as to restore a user use scene.
The OP database is established by the following steps:
a. Archiving test results, including: obtaining a trend graph of OP size to performance; obtaining a trend graph of OP size to NAND service life; obtaining a trend chart of OP size to garbage recovery efficiency; obtaining TBW (Total Bytes Written) data trend graphs of the OP size under a specific user model;
b. Establishing a database of quantitative relations between OP and performance, WA (Write Amplification), EC (Erase Count), WL (Wear Leveling) efficiency, GC (Garbage Collection) efficiency and TBW under different use scenes; and perfecting all corresponding test data of the OP from the minimum value to the maximum value through a large number of tests.
C. Repeating steps a and b to refine the data for different NAND products.
The OP database is used for OP inquiry and training of a prediction model.
The prediction model, i.e. the OP recommendation algorithm in fig. 2, is used for predicting the recommended OP setting value through the artificial neural network model. For example, BP networks, complex mappings between inputs (e.g., OP size adjustments) and outputs (e.g., WA, performance, lifetime, and TBW changes) can be established by learning patterns in the historical data. The mapping relation can capture nonlinear characteristics in the data, so that prediction of future states is realized.
Second, to make the predictions described above, a large amount of relevant data about OP sizing and its effects (i.e., data in the OP database) needs to be collected and used to train the artificial neural network model. Through continuous iteration and optimization, the model can gradually learn the internal rules and trends in the data, so that the prediction accuracy is improved.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents.
Claims (5)
1. A headspace adjustment method for a NAND product, characterized by: the method comprises the following steps:
Step 1, determining the NAND requirement;
Step 2, evaluating the current OP value of the NAND;
Step 3, according to the requirement in the step 1, inquiring a corresponding OP value in an OP database; if the OP value exists, the OP value of the NAND is adjusted to be the corresponding OP value, otherwise, the corresponding OP value is obtained through a prediction model, and then the OP value of the NAND is adjusted to be the corresponding OP value;
step 4, testing and verifying whether NAND meets the requirement in the step 1 through an OP test quantization tool set, if so, updating an OP database, otherwise, repeating the steps 3 to 4 until the requirement in the step 1 is met;
In the step 1, the NAND requirements include: performance requirements, cost requirements, lifetime requirements, and system stability requirements;
The OP test quantization tool set is used for performance test, wear balance test, garbage collection and user model test;
The OP database is established by the following steps:
archiving test results, including: obtaining a trend graph of OP size to performance; obtaining a trend graph of OP size to NAND service life; obtaining a trend chart of OP size to garbage recovery efficiency; obtaining TBW (Total Bytes Written) data trend graphs of the OP size under a specific user model;
Establishing a database of quantitative relations between OP and performance, WA (Write Amplification), EC (Erase Count of blocks), WL (Wear Leveling) efficiency, GC (Garbage Collection) efficiency and TBW under different use scenes;
C. repeating steps a and b to refine the data for different NAND products.
2. The headspace adjustment method for a NAND product according to claim 1, wherein: in the step 2, the evaluation is performed by an OP management tool.
3. The headspace adjustment method for a NAND product according to claim 2, wherein: the OP management tool is configured to obtain OP information of the NAND and adjust an OP value, where the OP information includes: current OP setting and OP adjustable range.
4. The headspace adjustment method for a NAND product according to claim 1, wherein: the prediction model is used for predicting the recommended OP setting value through the artificial neural network model.
5. The headspace adjustment method for a NAND product of claim 4, wherein: the OP database is used for training an artificial neural network model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410481719.5A CN118092813B (en) | 2024-04-22 | 2024-04-22 | Reserved space adjusting method for NAND product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410481719.5A CN118092813B (en) | 2024-04-22 | 2024-04-22 | Reserved space adjusting method for NAND product |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118092813A CN118092813A (en) | 2024-05-28 |
CN118092813B true CN118092813B (en) | 2024-06-21 |
Family
ID=91142367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410481719.5A Active CN118092813B (en) | 2024-04-22 | 2024-04-22 | Reserved space adjusting method for NAND product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118092813B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103853786A (en) * | 2012-12-06 | 2014-06-11 | 中国电信股份有限公司 | Method and system for optimizing database parameters |
CN112034947A (en) * | 2020-09-02 | 2020-12-04 | 苏州浪潮智能科技有限公司 | Backboard design system for enhancing server hard disk compatibility and parameter tuning method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US12008456B2 (en) * | 2019-06-28 | 2024-06-11 | Intel Corporation | Methods, apparatus, systems and articles of manufacture for providing query selection systems |
CN115858660A (en) * | 2021-09-23 | 2023-03-28 | 中移(苏州)软件技术有限公司 | Parameter recommendation method and device and computer storage medium |
CN114564460B (en) * | 2022-02-25 | 2024-01-19 | 苏州浪潮智能科技有限公司 | Parameter tuning method, device, equipment and medium based on distributed storage system |
CN115509844A (en) * | 2022-09-28 | 2022-12-23 | 苏州浪潮智能科技有限公司 | Method, system, device and medium for optimizing performance of NVMe hard disk based on AMD platform |
CN116795799A (en) * | 2023-08-02 | 2023-09-22 | 深圳玖合精工科技有限公司 | Automatic defragmentation method for hard disk files, computer equipment and storage medium |
-
2024
- 2024-04-22 CN CN202410481719.5A patent/CN118092813B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103853786A (en) * | 2012-12-06 | 2014-06-11 | 中国电信股份有限公司 | Method and system for optimizing database parameters |
CN112034947A (en) * | 2020-09-02 | 2020-12-04 | 苏州浪潮智能科技有限公司 | Backboard design system for enhancing server hard disk compatibility and parameter tuning method |
Also Published As
Publication number | Publication date |
---|---|
CN118092813A (en) | 2024-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Hard drive failure prediction using decision trees | |
CN110413227B (en) | Method and system for predicting remaining service life of hard disk device on line | |
CN109752656B (en) | SOH (State of health) evaluation method for battery of electric vehicle under multi-time scale | |
CN109116444B (en) | PCA-kNN-based air quality model PM2.5Forecasting method | |
JP7152938B2 (en) | Machine learning model building device and machine learning model building method | |
CN107220907B (en) | Harmonic pollution user grading method adopting rank-sum ratio comprehensive evaluation | |
CN104281779A (en) | Abnormal data judging and processing method and device | |
CN111858108B (en) | Hard disk fault prediction method and device, electronic equipment and storage medium | |
WO2023226355A1 (en) | Dual-ion battery fault detection method and system based on multi-source perception | |
CN104866679B (en) | A kind of mechanical property Forecasting Methodology of switchgear | |
CN112862164A (en) | Dry clutch temperature prediction method based on dynamic neural network time sequence prediction | |
CN118092813B (en) | Reserved space adjusting method for NAND product | |
CN115270238A (en) | Dynamic load-based bridge static behavior prediction method | |
CN117592609B (en) | On-line monitoring method, monitoring terminal and storage medium for canal water utilization coefficient | |
CN110515537A (en) | A method of extending solid-state disk service life | |
CN117577157A (en) | Method, device, equipment and medium for processing solid state disk read request | |
CN113610266A (en) | Method and device for predicting failure of automobile part, computer device and storage medium | |
CN109634854B (en) | Method for detecting configuration abnormity of software engineering algorithm | |
CN115511230B (en) | Electric energy substitution potential analysis and prediction method | |
CN114840149B (en) | Method and system for analyzing timing stability of super flash memory | |
CN116682479A (en) | Method and system for testing enterprise-level solid state disk time delay index | |
CN101752008B (en) | Method for testing reliability of solid-state storage media | |
CN111767165B (en) | Data processing method, device and control equipment | |
CN110580932B (en) | Memory cell quality measurement method applied to wear leveling | |
CN114492914A (en) | Rock mass characterization unit volume value prediction method and system based on machine learning |
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 |