CN117874101A - Elastic distributed data storage system, method and device and electronic equipment - Google Patents
Elastic distributed data storage system, method and device and electronic equipment Download PDFInfo
- Publication number
- CN117874101A CN117874101A CN202410032070.9A CN202410032070A CN117874101A CN 117874101 A CN117874101 A CN 117874101A CN 202410032070 A CN202410032070 A CN 202410032070A CN 117874101 A CN117874101 A CN 117874101A
- Authority
- CN
- China
- Prior art keywords
- data
- data storage
- file
- load
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013500 data storage Methods 0.000 title claims abstract description 169
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 238000011056 performance test Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013341 scale-up Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of data storage, and discloses an elastic distributed data storage system, an elastic distributed data storage method, an elastic distributed data storage device and electronic equipment, wherein the elastic distributed data storage system comprises the following components: the system comprises an API interface module and a data storage node, wherein the API interface module is electrically connected with a main naming space, the main naming space is electrically connected with a data storage layout adjustment module, the data storage layout adjustment module is electrically connected with a data storage node, and the data storage node is electrically connected with a load prediction, load monitoring and performance test module.
Description
Technical Field
The invention relates to the technical field of data storage, in particular to an elastic distributed data storage system, an elastic distributed data storage method, an elastic distributed data storage device and electronic equipment.
Background
With the development of business, various data of an enterprise system are rapidly increased and accumulated data are accumulated in daily life, an existing storage system is simply expanded by a Scale Up (vertical expansion) mode, the requirement of data growth is met by continuously increasing storage capacity, and bandwidth and computing capacity are not synchronously increased. Thus, the overall storage system quickly reaches a performance bottleneck, and the difficulty of continuing expansion is greatly increased.
In order to solve the above problems, there are two solutions in the conventional manner: firstly, a storage engine with stronger performance (the Clarion system of EMC and the FAS series of NetApp are adopted, and a mode of adding a CPU and a memory of a controller is adopted to provide stronger performance), but the mode has the problem of high price; another approach is to have an additional purchased separate storage system, which in turn increases the complexity of the management and is also relatively expensive.
In addition, in order to realize the elastic control of the user storage system, the control of data movement is required continuously, but frequent data movement can move data to the overloaded data storage nodes, and new performance problems are brought to the system.
Disclosure of Invention
The present invention is directed to a flexible distributed data storage system, a method, an apparatus and an electronic device, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions: a resilient distributed data storage system comprising: the system comprises an API interface module and a data storage node, wherein the API interface module is electrically connected with a main naming space, the main naming space is electrically connected with an auxiliary naming space, the main naming space is electrically connected with a data storage layout adjustment module, the data storage layout adjustment module is electrically connected with the data storage node, the data storage node is electrically connected with a load prediction, load monitoring and performance test module, and a plurality of data storage nodes are arranged;
the API interface is used for externally accessing the elastic distributed data storage system, and the main naming space is used for receiving and processing file read-write requests and reading data blocks from the data storage nodes or writing the data blocks into the data storage nodes according to the read-write requests.
Furthermore, the performance test module is used for performing performance benchmark test on the single data storage node in an offline state, constructing a performance boundary model by a statistical machine learning method, judging whether the data node is in an overload state or not, and guiding the generation of a data storage layout adjustment strategy.
Further, load monitoring is used for monitoring the load of each data storage node in real time, and load prediction is used for giving prediction to the load of each data storage node in combination with historical data.
Further, the data storage layout adjustment module is configured to generate a current data storage layout policy in combination with the load-monitored data, so as to perform data movement on the data storage nodes at the bottom layer.
A resilient distributed data storage method includes a resilient distributed data storage system.
Further, the method comprises the following steps:
s1: performing performance benchmark test on the single data storage node in an offline state, and after the test is completed, receiving a file reading request, wherein the file reading request comprises storage address list information of a file;
s2: reading corresponding data blocks from corresponding data storage nodes according to the storage address list information of the file, and integrating the read data blocks into complete data;
s3: receiving a file writing request, wherein the file writing request comprises the size of a file and complete data of the file;
s4: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
s5: monitoring the load of each data storage node through load monitoring;
s6: giving predictions for the load of each of the data storage nodes by load prediction in combination with historical data;
s7: generating a current data storage layout strategy by combining the load monitored data through a data storage layout adjustment module;
s8: distributing a storage address to each data block in the S4 to obtain storage address list information corresponding to the complete data;
s9: and moving the data in the data storage nodes, and storing each data block into the data storage nodes designated by the storage addresses.
Further, in S2, the read data blocks are processed and integrated into a complete data, namely, each data block is decompressed and decoded, and is combined into a complete data, in S4, after the complete data is divided into at least one data block, each divided data block is further subjected to packet coding; s4, determining that the size of the file is smaller than a threshold value according to a preset segmentation rule, defining the file as a small file, not segmenting the small file, and distributing a storage address for the small file; and S9, after the data storage node receives the data block, decoding the data block, checking the integrity of the decoded data block, and storing the data block after judging that the data block is complete.
A resilient distributed data storage device, comprising:
a read request unit: receiving a file reading request, wherein the file reading request comprises storage address list information of a file;
reading processing unit: reading corresponding data blocks from corresponding data storage nodes according to the storage address list information of the file, and integrating the read data blocks into complete data;
write request unit: receiving a file writing request, wherein the file writing request comprises the size of a file and complete data of the file;
a data dividing unit: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
a storage allocation unit: the storage address is allocated to each data block so as to obtain storage address list information corresponding to the complete data;
a data storage unit: each data block is stored to a data storage node designated by a storage address.
Further, the method further comprises the following steps: load monitoring unit: monitoring the load of each data storage node;
load prediction unit: giving a prediction of each of said data storage node loads in combination with historical data;
data storage layout adjustment unit: and generating a current data storage layout strategy by combining the data of the load monitoring unit.
An electronic device, comprising: a CPU processor, a memory, and a computer readable program stored in the memory and executable by the processor, which when executed by the processor, implements the steps in the resilient distributed data storage method.
Compared with the prior art, the invention has the beneficial effects that:
the invention expands a file system fixed on a certain node to any plurality of nodes, each storage node can be read and written, effectively solves the problem of data storage, simultaneously carries out performance benchmark test on a single data node in a system before data movement, builds a performance boundary model through a statistical machine learning method, is used for judging whether the data node is in an overload state and guiding the generation of a data layout adjustment strategy, monitors the load of each data node in real time, gives a prediction on the load of each data node in combination with historical data, takes the current data storage layout as the input of a data storage layout adjustment strategy generation algorithm, solves the data storage layout adjustment strategy by using a data storage layout adjustment strategy generation algorithm based on greedy thought on the basis of the performance model and the load prediction in combination with the current data storage layout, and finally carries out data movement on the bottom data node to form a complete elastic control;
according to the method, the data in the overloaded data storage nodes are dynamically moved to other nodes, so that the overlong data access time is avoided, the use experience is influenced, and the idle data storage nodes are subjected to data merging, so that the system resource expenditure is reduced, and different performance requirements are met.
Drawings
FIG. 1 is a schematic diagram of a module structure of a resilient distributed data storage system according to the present invention;
FIG. 2 is a flow chart of a method of resilient distributed data storage according to the present invention;
in the figure: 100. an API interface module; 2. a primary namespace; 300. a secondary namespace; 400. a data storage layout adjustment module; 5. load prediction; 6. load monitoring; 7. a performance test module; 800. and a data storage node.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Embodiment one: referring to fig. 1, the present invention provides a technical solution: a resilient distributed data storage system comprising: the API interface module 100 and the data storage node 800, the API interface module 100 is electrically connected with a main naming space 200, the main naming space 200 is electrically connected with an auxiliary naming space 300, the main naming space 200 is electrically connected with a data storage layout adjustment module 400, the data storage layout adjustment module 400 is electrically connected with the data storage node 800, the data storage node 800 is electrically connected with a load prediction module 500, a load monitoring module 600 and a performance test module 700, and a plurality of data storage nodes are arranged;
the API interface is used for externally accessing the flexible distributed data storage system, and the main namespace 200 is used for receiving and processing file read-write requests, and reading data blocks from the data storage node 800 or writing data blocks to the data storage node according to the read-write requests.
And the modules of the system use a NIO network framework with high expansibility and high performance to perform information interaction. The master namespace 200 maintains the entire system address directory tree and all files under the address directory, enforces copy policies, monitors the state of the data storage nodes, and accepts and processes requests incoming through the API interface. The secondary namespace 300 is a cold backup of the primary namespace 200, preventing a single point risk, and will work in place of the primary namespace 200 when the primary namespace 200 is not working properly. The data storage node 800 stores and retrieves data blocks as needed and periodically sends their information to the primary namespace 200.
The performance test module 700 is configured to perform performance benchmark test on a single data storage node 800 in an offline state, and construct a performance boundary model by using a statistical machine learning method to determine whether the data node is in an overload state, and instruct generation of a data storage layout adjustment policy.
Load monitoring 600 is used to monitor the load of each data storage node 800 in real time, and load prediction 500 is used to give predictions for each data storage node 800 load in combination with historical data.
The data storage layout adjustment module 400 is configured to generate a current data storage layout policy in conjunction with the data of the load monitor 600, so as to perform data movement on the underlying data storage nodes 800.
When the load fluctuation of the data storage node 800 is large, the underlying data storage needs to be dynamically and adaptively adjusted through the system to realize elastic control.
Performing performance benchmark test on a single data node in a system before data movement, constructing a performance boundary model through a statistical machine learning method, judging whether the data node is in an overload state or not, guiding generation of a data layout adjustment strategy, monitoring load of each data node in real time, giving prediction to the load of each data node by combining historical data, combining a current data storage layout as input of a data storage layout adjustment strategy generation algorithm, solving the data storage layout adjustment strategy by using the data storage layout adjustment strategy generation algorithm based on greedy thought based on the performance model and the load prediction and combining the current data storage layout, and finally performing data movement on the bottom data node to form a complete elastic control;
when the data node processes excessive data access requests and is in an overload state, the performance requirements of different users on the data access response time cannot be met, and the user experience is affected; when the data nodes are in an idle state due to small data access quantity, the resource utilization rate of the data nodes is low, and the method of the embodiment realizes the self-adaptive adjustment of user data, namely, overheat data in the overload server is moved to other data nodes so as to ensure that the performance requirements of data access of different tenants are met; and the idle server performs data merging to reduce the system resource overhead.
Embodiment two: referring to fig. 2, the present invention provides a technical solution: a resilient distributed data storage method includes a resilient distributed data storage system. The method comprises the following steps:
s1: performing performance benchmark test on a single data storage node 800 in an offline state, and after the test is completed, receiving a file reading request, wherein the file reading request comprises storage address list information of a file;
s2: reading corresponding data blocks from the corresponding data storage nodes 800 according to the storage address list information of the file, and integrating the read data blocks into one complete data;
s3: receiving a writing request of a file, wherein the writing request of the file comprises the size of the file and the complete data of the file;
s4: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
s5: monitoring the load of each data storage node 800 by load monitoring 600;
s6: giving a prediction of each data storage node 800 load by load prediction 500 in combination with historical data;
s7: generating a current data storage layout policy by the data storage layout adjustment module 400 in combination with the data of the load monitor 600;
s8: distributing a storage address to each data block in the S4 to obtain storage address list information corresponding to the complete data;
s9: data in the data storage node 800 is moved and each data block is stored to the data storage node 800 designated by the storage address.
S2, processing and integrating the read data blocks into one complete data, namely decompressing and decoding the data blocks, merging the data blocks into one complete data, and after dividing the complete data into at least one data block, carrying out packet coding on each divided data block; s4, judging that the size of the file is smaller than a threshold value according to a preset segmentation rule, defining the file as a small file, not segmenting the small file, and distributing a storage address for the small file; and S9, after the data storage node 10 receives the data block, decoding the data block, checking the integrity of the decoded data block, and storing the data block after judging that the data block is complete.
The method comprises the steps of expanding a file system fixed on a certain node to any plurality of nodes, reading and writing each storage node, effectively solving the storage problem of data, simultaneously carrying out performance benchmark test on a single data node in a system before data movement, constructing a performance boundary model by a statistical machine learning method, judging whether the data node is in an overload state or not and guiding the generation of a data layout adjustment strategy, monitoring the load of each data node in real time, giving a prediction on the load of each data node by combining historical data, taking the current data storage layout as the input of a data storage layout adjustment strategy generation algorithm, solving the data storage layout adjustment strategy by using a data storage layout adjustment strategy generation algorithm based on greedy thought on the basis of the performance model and the load prediction and combining the current data storage layout, and finally carrying out data movement on the bottom data node to form a complete elastic control;
and dynamically moving the data in the overloaded data storage nodes to other nodes, avoiding overlong data access time, influencing the use experience, and merging the data of the idle data storage nodes 800 to reduce the system resource overhead and meet different performance requirements.
Embodiment III: the invention provides a technical scheme that: a resilient distributed data storage device, comprising:
a read request unit: receiving a file reading request, wherein the file reading request comprises storage address list information of a file;
reading processing unit: reading corresponding data blocks from corresponding data storage nodes according to the storage address list information of the file, and integrating the read data blocks into complete data;
write request unit: receiving a writing request of a file, wherein the writing request of the file comprises the size of the file and the complete data of the file;
a data dividing unit: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
a storage allocation unit: the storage address list information is configured to allocate a storage address for each data block so as to obtain storage address list information corresponding to the complete data;
a data storage unit: each data block is stored to a data storage node 800 designated by a storage address.
Further comprises: load monitoring unit: monitoring the load of each data storage node 800;
load prediction unit: giving predictions of each data storage node 800 load in combination with historical data;
data storage layout adjustment unit: and generating a current data storage layout strategy by combining the data of the load monitoring unit.
The data storage unit decodes the received data block, verifies the integrity of the decoded data block, and stores the data block after judging that the data block is complete. And if the size of the file is judged to be smaller than the threshold value according to the preset segmentation rule, defining the file as a small file, not needing to be segmented, and distributing a storage address for the small file.
The above step flow can be divided into a large file reading process and a writing process, and a small file reading process and a writing process.
Specifically, for the reading process of a large file, a file reading request is sent to a main naming space through an API interface, data block storage address list information corresponding to the file is obtained, data blocks are read from each data storage unit according to the data block storage address list information, and all the data blocks are decoded and combined to obtain complete data of the file.
Aiming at the writing process of the large file, the large file is cut into a plurality of data blocks according to a preset segmentation rule, namely the size of the data blocks configured by the system, the size of the cut data blocks accords with a data block segmentation strategy configured by the system, and the cut data blocks are subjected to packet coding one by one. And sending a writing request to a main naming space, wherein the main naming space allocates a storage address for the data block, and the data block is transmitted to a corresponding data storage node for storage according to the storage address. After receiving the data block, the data storage node decodes the data block, verifies the integrity of the data block, stores the data block, and feeds back the storage result to the main naming space.
And aiming at the reading process of the small file, sending a reading request to a main naming space, acquiring a corresponding storage address, reading the data of the small file from a designated node according to the storage address, and decoding the data block to obtain complete data.
And aiming at the writing process of the small file, a writing request is sent, the small file data block is subjected to package coding, a key and a storage address are distributed to the small file by a main naming space, and the small file data block is transmitted to a corresponding data storage node for archiving and storing according to the storage address. The data storage node decodes the data block, then checks the integrity, and files and stores the data block after ensuring the integrity.
Embodiment four: the invention provides a technical scheme that: an electronic device, comprising: a CPU processor, a memory, and a computer readable program stored in the memory and executable by the processor, which when executed by the processor, implements the steps in the resilient distributed data storage method.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Claims (10)
1. A resilient distributed data storage system comprising: an API interface module (100) and a data storage node (800), characterized by: the API interface module (100) is electrically connected with a main naming space (200), the main naming space (200) is electrically connected with an auxiliary naming space (300), the main naming space (200) is electrically connected with a data storage layout adjustment module (400), the data storage layout adjustment module (400) is electrically connected with data storage nodes (800), the data storage nodes (800) are electrically connected with load prediction (500), load monitoring (600) and performance test modules (700), and the data storage nodes are multiple;
the API interface is used for externally accessing the elastic distributed data storage system, and the main naming space (200) is used for receiving and processing file read-write requests and reading data blocks from the data storage node (800) or writing the data blocks to the data storage node according to the read-write requests.
2. The resilient distributed data storage system of claim 1, wherein: the performance test module (700) is used for performing performance benchmark test on the single data storage node (800) in an offline state, constructing a performance boundary model through a statistical machine learning method, and determining whether the data node is in an overload state or not and guiding the generation of a data storage layout adjustment strategy.
3. The resilient distributed data storage system of claim 1, wherein: the load monitoring (600) is used for monitoring the load of each data storage node (800) in real time, and the load prediction (500) is used for giving predictions for the load of each data storage node (800) in combination with historical data.
4. The resilient distributed data storage system of claim 1, wherein: the data storage layout adjustment module (400) is configured to generate a current data storage layout policy in conjunction with data of the load monitor (600) to perform data movement on the underlying data storage nodes (800).
5. The elastic distributed data storage method is characterized in that: comprising the resilient distributed data storage system of any one of claims 1-4.
6. The resilient distributed data storage method of claim 5, wherein: the method comprises the following steps:
s1: performing performance benchmark test on the single data storage node (800) in an offline state, and after the test is completed, receiving a file reading request, wherein the file reading request comprises storage address list information of files;
s2: reading corresponding data blocks from corresponding data storage nodes (800) according to the storage address list information of the file, and integrating the read data blocks into complete data;
s3: receiving a file writing request, wherein the file writing request comprises the size of a file and complete data of the file;
s4: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
s5: monitoring the load of each data storage node (800) by means of load monitoring (600);
s6: -giving predictions of the load of each of said data storage nodes (800) by load prediction (500) in combination with historical data;
s7: generating, by the data storage layout adjustment module (400), a current data storage layout policy in combination with the data of the load monitor (600);
s8: distributing a storage address to each data block in the S4 to obtain storage address list information corresponding to the complete data;
s9: data in the data storage node (800) is moved and each data block is stored in the data storage node (800) designated by the storage address.
7. The resilient distributed data storage method of claim 6, wherein: s2, processing and integrating the read data blocks into one complete data, namely decompressing and decoding the data blocks, merging the data blocks into one complete data, and after dividing the complete data into at least one data block in S4, carrying out packet coding on each divided data block; s4, determining that the size of the file is smaller than a threshold value according to a preset segmentation rule, defining the file as a small file, not segmenting the small file, and distributing a storage address for the small file; and S9, after the data storage node (10) receives the data block, decoding the data block, checking the integrity of the decoded data block, and storing the data block after judging that the data block is complete.
8. Elasticity distributed data storage device, its characterized in that: comprising the following steps:
a read request unit: receiving a file reading request, wherein the file reading request comprises storage address list information of a file;
reading processing unit: reading corresponding data blocks from corresponding data storage nodes according to the storage address list information of the file, and integrating the read data blocks into complete data;
write request unit: receiving a file writing request, wherein the file writing request comprises the size of a file and complete data of the file;
a data dividing unit: dividing the complete data into at least one data block according to the size of the file and a preset dividing rule;
a storage allocation unit: the storage address is allocated to each data block so as to obtain storage address list information corresponding to the complete data;
a data storage unit: each data block is stored to a data storage node (800) designated by a storage address.
9. The resilient distributed data storage method of claim 8, wherein: further comprises: load monitoring unit: monitoring the load of each data storage node (800);
load prediction unit: -giving predictions for each of said data storage node (800) loads in combination with historical data;
data storage layout adjustment unit: and generating a current data storage layout strategy by combining the data of the load monitoring unit.
10. An electronic device, comprising: a CPU processor, a memory and a computer readable program stored in the memory and executable by the processor, characterized in that the computer readable program when executed by the processor implements the steps of the resilient distributed data storage method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032070.9A CN117874101A (en) | 2024-01-10 | 2024-01-10 | Elastic distributed data storage system, method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032070.9A CN117874101A (en) | 2024-01-10 | 2024-01-10 | Elastic distributed data storage system, method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117874101A true CN117874101A (en) | 2024-04-12 |
Family
ID=90578769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410032070.9A Pending CN117874101A (en) | 2024-01-10 | 2024-01-10 | Elastic distributed data storage system, method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874101A (en) |
-
2024
- 2024-01-10 CN CN202410032070.9A patent/CN117874101A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11237871B1 (en) | Methods, systems, and devices for adaptive data resource assignment and placement in distributed data storage systems | |
| CN105205014B (en) | A kind of date storage method and device | |
| CN110427284B (en) | Data processing method, distributed system, computer system, and medium | |
| US7590816B2 (en) | Computer system, management computer and storage system, and storage area allocation amount controlling method | |
| US10956990B2 (en) | Methods and apparatuses for adjusting the distribution of partitioned data | |
| US20220075757A1 (en) | Data read method, data write method, and server | |
| CN112269661B (en) | Partition migration method and device based on Kafka cluster | |
| CN109840051B (en) | Data storage method and device of storage system | |
| US20240201880A1 (en) | Resource Allocation Method and Apparatus | |
| US11403026B2 (en) | Method, device and computer program product for managing storage system | |
| CN115686342A (en) | Data storage method and device in storage system | |
| CN103685359B (en) | Data processing method and device | |
| CN115208900B (en) | Multi-cloud architecture cloud service resource scheduling method based on blockchain and game model | |
| CN115981559A (en) | Distributed data storage method and device, electronic equipment and readable medium | |
| CN116401043A (en) | Execution method of computing task and related equipment | |
| CN117874101A (en) | Elastic distributed data storage system, method and device and electronic equipment | |
| US20090288089A1 (en) | Method for prioritized event processing in an event dispatching system | |
| CN106339279B (en) | Service recovery method and device | |
| CN111708489B (en) | Method and equipment for improving hard disk service quality | |
| CN114625474A (en) | Container migration method and device, electronic equipment and storage medium | |
| CN111399763B (en) | Method, device, system, equipment and storage medium for data storage | |
| CN114328604B (en) | Method, device and medium for improving cluster data acquisition capacity | |
| US20240311002A1 (en) | Scaling management apparatus and scaling management method for storage system including storage nodes | |
| CN118193540B (en) | Index processing method, device, electronic equipment and readable storage medium | |
| CN109815192B (en) | Method and device for managing embedded system memory |
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 |