CN116610756A - Distributed database self-adaptive copy selection method and device - Google Patents
Distributed database self-adaptive copy selection method and device Download PDFInfo
- Publication number
- CN116610756A CN116610756A CN202310868595.1A CN202310868595A CN116610756A CN 116610756 A CN116610756 A CN 116610756A CN 202310868595 A CN202310868595 A CN 202310868595A CN 116610756 A CN116610756 A CN 116610756A
- Authority
- CN
- China
- Prior art keywords
- copy
- gateway node
- reading
- nodes
- distributed database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010187 selection method Methods 0.000 title claims abstract description 19
- 230000002068 genetic effect Effects 0.000 claims abstract description 25
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 20
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 7
- 108090000623 proteins and genes Proteins 0.000 claims description 6
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012795 verification 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
- G06F16/278—Data partitioning, e.g. horizontal or vertical partitioning
-
- 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
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1458—Management of the backup or restore process
- G06F11/1464—Management of the backup or restore process for networked environments
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2246—Trees, e.g. B+trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/80—Database-specific techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/82—Solving problems relating to consistency
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a self-adaptive copy selection method and a self-adaptive copy selection device for a distributed database, which belong to the field of distributed databases, and the technical problem to be solved by the invention is how to quickly select copies for improving efficiency, and the technical scheme is as follows: s101, a gateway node analyzes an SQL sentence and acquires a data range to be read in the sentence; s102, filtering out the copy of the old version from the copy cache information, and acquiring the Range size with the latest version; s103, transferring the copy information parameters obtained in the step S102 to a genetic evolution algorithm, and then generating population starting iteration about selectable copy distribution information; s104, setting a cut-off mechanism; s105, the gateway node sends the data to the corresponding node for reading; s106, the results of the nodes are collected to the gateway node and returned to the client. Compared with the prior art, the genetic evolution can obtain good optimization results in a short time.
Description
Technical Field
The invention relates to the field of distributed databases, and particularly provides a distributed database self-adaptive copy selection method and device.
Background
Reading data, which is a common operation in a database and is commonly used for a first operator in an SQL statement execution plan; the read data operator is a basic operator in both OLTP scenarios of various transaction models and OLAP scenarios of computational analysis models.
The performance of the distributed database is mainly reflected in that shared-nothing nodes in the cluster store partial data and can independently perform parallel computation, and when the task of one node is completed and waits for other nodes, the phenomenon of unbalanced load occurs, so that resources are idle.
The distributed database adopts a multi-copy strategy on storage, namely each data after the data table is partitioned is stored in a plurality of nodes at the same time, and the plurality of nodes are selected for reading task allocation. The amount of data per data is different, as is the delay between the node and the gateway node. The main technical implementation scheme for realizing the load balancing based on the combination optimization problem is realized by distributing the reading tasks to the nodes and ensuring the balance of the reading task quantity on the nodes.
The related art of replica selection policies typically employ a proximity principle in a distributed database to select the node that has the shortest delay from the gateway node. I.e. the range of data known to the gateway node to be read, which range involves three copies of each piece of data, i.e. three nodes, to select the node with the shortest delay from the gateway node, reducing the time delay for the request to be sent and returned. And for the strong consistency reading, namely acquiring the latest version data to ensure that the data is up-to-date, considering the consensus algorithm, and selecting a leader node in the consensus algorithm to ensure the strong consistency reading due to the fact that the latest version of the data is ensured.
The performance of the distributed database is mainly reflected in that a plurality of nodes can work in parallel to improve the efficiency of a single machine mode. However, in the task allocation process of the read data, no matter whether the nearby principle or the selection based on the consensus algorithm can not ensure the balance of the read task quantity on the plurality of nodes, the phenomenon that the node with small read task quantity among the plurality of nodes for reading the data firstly completes the node waiting for large read task quantity, and the resource is idle is caused, so that the efficiency of the distributed database is reduced.
In addition, in the generation of the distributed database physical plan, the nodes participating in SQL execution are all the nodes involved in the data reading process. The specific operators into which other operators on the optimal logical plan tree are converted are stacked on these operators reading data, i.e. the spreadsheet operators, in a bottom-up direction of the optimal logical plan tree. The whole physical plan is usually started by reading data, the efficiency of reading the data is low, and the unbalanced allocation of the reading task quantity can seriously influence the execution efficiency of subsequent operators in the physical plan.
How to select a copy is a key for determining nodes participating in reading in a distributed database and selecting a node related to the subsequent execution efficiency of a distributed execution plan, and is a problem to be solved by those skilled in the art.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a distributed database self-adaptive copy selection method with strong practicability.
The invention further aims to provide a distributed database self-adaptive copy selection device which is reasonable in design, safe and applicable.
The technical scheme adopted for solving the technical problems is as follows:
the self-adaptive duplicate selection method for the distributed database is characterized in that the distributed database is divided into two types of strong consistency reading and delay reading;
the strong consistency reading self-adaptive hybrid copy selection method comprises the following steps:
s101, a gateway node analyzes an SQL sentence and acquires a data range to be read in the sentence;
s102, filtering out the copy of the old version from the copy cache information, and acquiring the Range size with the latest version;
s103, transferring the copy information parameters obtained in the step S102 to a genetic evolution algorithm, and then generating population starting iteration about selectable copy distribution information;
s104, setting a cut-off mechanism;
s105, the gateway node sends the data to the corresponding node for reading;
s106, collecting results of all the nodes to the gateway node and returning the results to the client;
the delay reading self-adaptive hybrid copy selection method comprises the following steps:
s201, a gateway node analyzes an SQL sentence, and obtains a data range to be read in the SQL sentence;
s202, transmitting the distribution information acquired in the step S201 as parameters into a genetic evolution algorithm for iteration;
s203, judging a genetic evolution algorithm and a truncation mechanism;
s204, the gateway node sends the data to the corresponding node for reading;
s205, the results of the nodes are collected to the gateway node and returned to the client.
Further, in step S101, the gateway node parses the SQL statement, obtains a data Range to be read in the SQL statement, and obtains distribution information of each Range in the data Range according to the tree structure indexed in the distribution layer.
Further, in step S102, the copy of the old version is filtered from the copy cache information, the Range size with the latest version is obtained, and meanwhile, the difference value between the maximum task reading amount and the minimum task reading amount in all the nodes is obtained by parallel running of a default copy selection policy of the system;
the default copy selection policy enables a single simple look-ahead acquisition.
Further, in step S103, the copy information parameters obtained in step S102 are transferred to the genetic evolutionary algorithm, and then the population related to the selectable copy distribution information is generated to start iteration, the iteration process is formed by cross variation, and each iteration round can select the best gene to obtain the difference value between the current maximum task amount and the minimum task amount.
Further, in step S104, a cut-off mechanism is set, that is, the minimum difference obtained in a period of time during which the genetic evolution algorithm operates is smaller than the difference obtained by the default copy selection policy of the system, and is smaller than the amount of reading tasks that can be performed by the hard disk at the same time under the condition of the hardware of the network.
Further, in step S105, the copy selection result obtained in step S104 is obtained by the gateway node in the generation of the physical plan, and then the physical plans of other operators are generated on the read table operator from bottom to top, and then sent to the corresponding node by the gateway node for reading.
Further, in step S201, the gateway node parses the SQL statement to obtain the data range to be read in the statement. Acquiring the distribution information of each Range in the data Range according to the tree structure indexed in the distribution layer;
in step S202, the distribution information obtained in step S201 is also transmitted as parameters to the genetic evolution algorithm for iteration, each gene segment has 3 nodes which can be mutated, and the default copy selection strategy of the parallel operation system obtains the difference value between the maximum task reading amount and the minimum task reading amount in all the nodes;
the default copy selection policy enables a single simple look-ahead acquisition.
Further, in step S204, the copy selection result obtained in step S203 is obtained by the gateway node in the generation of the physical plan, and then the physical plans of other operators are generated on the read table operator from bottom to top, and then sent to the corresponding node by the gateway node for reading.
Further, in step S205, the results of the nodes are collected into gateway nodes and returned to the client, and the hash connection result of each node is obtained as a union, that is, the final hash connection result.
A distributed database adaptive replica selection apparatus, comprising: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform a distributed database adaptive replica selection method.
Compared with the prior art, the distributed database self-adaptive copy selection method and device have the following outstanding beneficial effects:
the distribution information of the obtained copy is obtained in the cache, so that time expenditure is not brought. The distribution information of the copies is used as parameters to be transmitted into a genetic evolution algorithm to carry out iteration time with maximum cross variation, the time complexity of population generation and the time complexity of each iteration are respectively(N is the number of data blocks read), spatial complexity is +.>. It can be seen that genetic evolution can give good optimization results in a very short time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a distributed database adaptive replica selection method;
FIG. 2 is a diagram of distribution information of replicas in a distributed database adaptive replica selection method.
Detailed Description
In order to provide a better understanding of the aspects of the present invention, the present invention will be described in further detail with reference to specific embodiments. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. 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.
A preferred embodiment is given below:
in the self-adaptive copy selection method of the distributed database in the embodiment, the client is only connected with one node in the cluster, the node is called a gateway node, and the gateway node converts the SQL request into read-write operation of the bottom layer storage and coordinates node execution of distributed query processing. And is responsible for responding the query results to the client. The storage engine of the switch database is based on a RocksDB (Rocks database) stored by key values, each node is provided with a hard disk, and one hard disk corresponds to one RocksDB (Rocks database) instance. The switch database adopts horizontal data slicing, and the key space of the data is divided into a plurality of disjoint data blocks continuously by using Range partitioning by a distribution layer, wherein the data blocks are called Ranges, and the Range (data Range) is copied for 3 copies and distributed on different nodes in the cluster. As shown in FIG. 1, each table in the open database corresponds to a contiguous portion of the key space, and the distribution layer divides the table into ranges by Range partitions.
The distributed database is divided into two types of strong consistency reading and delay reading;
the method for selecting the self-adaptive hybrid copy with strong consistency comprises the following steps:
s101, a gateway node analyzes an SQL sentence and acquires a data range to be read in the sentence;
the gateway node analyzes the SQL statement and obtains the data range to be read in the statement. And acquiring the distribution information of each Range in the data Range according to the tree structure indexed in the distribution layer. As shown in fig. 2, taking the data Range [ a, d ] as an example, three ranges of distributed information of [ a, b ], [ b, c ], [ c, d ] can be obtained, namely [1,3,4], [2,4,5], [2,3,5].
S102, filtering out the copy of the old version from the copy cache information, and acquiring the Range size with the latest version;
and filtering the old version copy from the copy cache information, and acquiring the Range size with the latest version. And simultaneously, the default copy selection strategy of the parallel operation system acquires the difference value between the maximum task reading quantity and the minimum task reading quantity in all the nodes.
The default copy selection policy may be obtained in advance due to a single simple implementation.
S103, transferring the copy information parameters obtained in the step S2 to a genetic evolution algorithm, and then generating population starting iteration about selectable copy distribution information;
and (3) transferring the copy information parameters obtained in the step (S2) to a genetic evolution algorithm, and then generating a population starting iteration about selectable copy distribution information. The iteration process consists of cross variation, and each iteration round can select the best gene to obtain the difference value between the current maximum task reading quantity and the minimum task reading quantity.
S104, setting a cut-off mechanism;
as the Range distribution of the switch database is redistributed every time the switch is started, the copy selection of the system can obtain good load balance under some distribution information through experimental verification. In order to enable the system to adaptively select two strategies so that the maximum benefit can be obtained under any distribution condition, a cut-off mechanism is arranged, namely, the minimum difference value which can be obtained within 100ms of running a genetic evolution algorithm is smaller than the difference value obtained by the default copy selection strategy of the system, and the minimum difference value is smaller than the amount of reading tasks which can be carried out by a hard disk under the condition of the hardware and the network in 100 ms.
The phenomenon that the resource is idle can be improved by the copy selection strategy of the genetic evolution algorithm due to the fact that the load imbalance caused by the default copy selection strategy of the system can be judged, and the execution efficiency of operators is improved. If the genetic evolution algorithm fails to obtain good feedback in the setting time, the default copy selection strategy of the system is used for uniformly distributing the reading task to each node, and the phenomenon of resource idling and waiting does not occur.
S105, the gateway node sends the data to the corresponding node for reading;
the copy selection result obtained in the step S4 is obtained by the gateway node in the process of generating the physical plan, then the physical plans of other operators are generated on the meter reading operator from bottom to top, and then the physical plans are sent to the corresponding nodes by the gateway node for reading.
S106, the results of the nodes are collected to the gateway node and returned to the client.
The method for selecting the delay reading self-adaptive hybrid copy comprises the following steps:
s201, a gateway node analyzes an SQL sentence, and obtains a data range to be read in the SQL sentence;
the gateway node analyzes the SQL statement and obtains the data range to be read in the statement. And acquiring the distribution information of each Range in the data Range according to the tree structure indexed in the distribution layer.
S202, transmitting the distribution information acquired in the step S1 as parameters into a genetic evolution algorithm for iteration;
because the latest version of the Range copy is not required to be ensured, the distribution information acquired in the step S1 is taken as a parameter and also transmitted to a genetic evolution algorithm for iteration, and under the scene, each gene segment has 3 nodes for variation.
And simultaneously, the default copy selection strategy of the parallel operation system acquires the difference value between the maximum task reading quantity and the minimum task reading quantity in all the nodes. The default copy selection policy may be obtained in advance due to a single simple implementation.
S203, judging a genetic evolution algorithm and a truncation mechanism;
similar to step S4 in the strong consistency reading scenario, to implement the adaptive hybrid copy selection strategy, the genetic evolution algorithm needs to be combined with the judgment of the truncation mechanism, so as to obtain the maximum benefit under various distribution information conditions.
S204, the gateway node sends the data to the corresponding node for reading;
and 3, the copy selection result obtained in the step is obtained by the gateway node in the process of generating the physical plan, the physical plans of other operators are generated on the meter reading operator from bottom to top, and then the physical plans are sent to the corresponding nodes by the gateway node for reading.
S205, the results of the nodes are collected to the gateway node and returned to the client. The hash connection result of each node is the final hash connection result by union.
The following table compares the selection results with respect to an increase in the amount of read data:
the performance of the adaptive replica selection strategy was tested on the cockreach db database and compared to the basic scheme in the system. The table above shows the load balancing degree brought by the two modes of selecting and comparing the copies by using the method of the system and the self-adaptive strategy along with the increase of the number of the data blocks, namely the difference value between the maximum reading task amount and the minimum reading task amount, and can be seen under the condition of any copy distribution. The method can well lead the reading task quantity to be evenly distributed on each node.
Based on the above method, a distributed database adaptive copy selection apparatus in this embodiment includes: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform a distributed database adaptive replica selection method.
The above specific embodiments are merely illustrative of specific cases of the present invention, and the scope of the present invention includes, but is not limited to, the specific embodiments described above, any suitable changes or substitutions made by one of ordinary skill in the art, which are consistent with the present invention, of a distributed database adaptive replica selection method and apparatus claims, and all fall within the scope of the present invention.
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 principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The self-adaptive duplicate selection method for the distributed database is characterized in that the distributed database is divided into two types of strong consistency reading and delay reading;
the strong consistency reading self-adaptive hybrid copy selection method comprises the following steps:
s101, a gateway node analyzes an SQL sentence and acquires a data range to be read in the sentence;
s102, filtering out the copy of the old version from the copy cache information, and acquiring the Range size with the latest version;
s103, transferring the copy information parameters obtained in the step S102 to a genetic evolution algorithm, and then generating population starting iteration about selectable copy distribution information;
s104, setting a cut-off mechanism;
s105, the gateway node sends the data to the corresponding node for reading;
s106, collecting results of all the nodes to the gateway node and returning the results to the client;
the delay reading self-adaptive hybrid copy selection method comprises the following steps:
s201, a gateway node analyzes an SQL sentence, and obtains a data range to be read in the SQL sentence;
s202, transmitting the distribution information acquired in the step S201 as parameters into a genetic evolution algorithm for iteration;
s203, judging a genetic evolution algorithm and a truncation mechanism;
s204, the gateway node sends the data to the corresponding node for reading;
s205, the results of the nodes are collected to the gateway node and returned to the client.
2. The method for adaptively selecting a copy of a distributed database according to claim 1, wherein in step S101, a gateway node parses an SQL statement, obtains a data Range to be read in the SQL statement, and obtains distribution information of each Range in the data Range according to a tree structure indexed in a distribution layer.
3. The method for adaptively selecting a copy of a distributed database according to claim 2, wherein in step S102, an old version of the copy is filtered from the copy cache information, a Range size having the latest version is obtained, and a default copy selection policy of a parallel operation system obtains a difference value between a maximum task amount and a minimum task amount of all nodes;
the default copy selection policy enables a single simple look-ahead acquisition.
4. A distributed database adaptive replica selection method as claimed in claim 3, wherein in step S103, the replica information parameters obtained in step S102 are transferred to a genetic evolution algorithm, and then a population start iteration is generated for selectable replica distribution information, the iteration process is composed of cross variation, and each iteration round selects the best gene to obtain the difference between the current maximum task amount and the current minimum task amount.
5. The method according to claim 4, wherein in step S104, a cut-off mechanism is set, that is, a minimum difference obtained in a period of time during which the genetic evolution algorithm operates is smaller than a difference obtained by a default copy selection policy of the system, and is smaller than a read task amount that can be performed by the hard disk in the same environment and in the same time.
6. The method according to claim 5, wherein in step S105, the copy selection result obtained in step S104 is obtained by the gateway node in generating the physical plan, and then the physical plans of other operators are generated on the read table operator from bottom to top, and then the physical plan is sent to the corresponding node by the gateway node for reading.
7. The method for adaptively selecting a copy of a distributed database according to claim 6, wherein in step S201, the gateway node parses an SQL statement, obtains a data Range to be read in the statement, and obtains distribution information of each Range in the data Range according to a tree structure indexed in a distribution layer;
in step S202, the distribution information obtained in step S201 is also transmitted as parameters to the genetic evolution algorithm for iteration, each gene segment has 3 nodes which can be mutated, and the default copy selection strategy of the parallel operation system obtains the difference value between the maximum task reading amount and the minimum task reading amount in all the nodes;
the default copy selection policy enables a single simple look-ahead acquisition.
8. The method according to claim 7, wherein in step S204, the copy selection result obtained in step S3 is obtained by the gateway node in generating the physical plan, and then the physical plans of other operators are generated on the read table operator from bottom to top, and then the physical plan is sent to the corresponding node by the gateway node for reading.
9. The method according to claim 8, wherein in step S205, the results of the nodes are collected into gateway nodes and returned to the client, and the hash connection result of each node is obtained as a final hash connection result by combining.
10. A distributed database adaptive replica selection apparatus, comprising: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor being configured to invoke the machine readable program to perform the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868595.1A CN116610756B (en) | 2023-07-17 | 2023-07-17 | Distributed database self-adaptive copy selection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868595.1A CN116610756B (en) | 2023-07-17 | 2023-07-17 | Distributed database self-adaptive copy selection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116610756A true CN116610756A (en) | 2023-08-18 |
| CN116610756B CN116610756B (en) | 2024-03-08 |
Family
ID=87685685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310868595.1A Active CN116610756B (en) | 2023-07-17 | 2023-07-17 | Distributed database self-adaptive copy selection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116610756B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593287A (en) * | 2013-10-30 | 2014-02-19 | 北京信息控制研究所 | Genetic-algorithm-based method for automatically generating data stream test cases |
| CN107103360A (en) * | 2017-03-31 | 2017-08-29 | 华南理工大学 | A kind of reliability application distribution distributed genetic algorithm based on mixed cloud |
| CN109740037A (en) * | 2019-01-02 | 2019-05-10 | 山东省科学院情报研究所 | The distributed online real-time processing method of multi-source, isomery fluidised form big data and system |
| WO2019144046A1 (en) * | 2018-01-19 | 2019-07-25 | Hyperdyne, Inc. | Distributed high performance computing using distributed average consensus |
| CN113449065A (en) * | 2021-06-29 | 2021-09-28 | 苏州链约科技有限公司 | Data deduplication-oriented decentralized storage method and storage device |
| CN113934374A (en) * | 2021-09-28 | 2022-01-14 | 北京理工大学 | Block chain multi-copy distribution and storage method based on genetic algorithm |
| CN114817402A (en) * | 2022-04-25 | 2022-07-29 | 山东浪潮科学研究院有限公司 | SQL execution optimization method of distributed database in multi-region deployment scene |
| CN115794854A (en) * | 2022-12-09 | 2023-03-14 | 华东师范大学 | Method for reading local linear consistency on copy based on Raft algorithm |
| US20230081900A1 (en) * | 2021-09-15 | 2023-03-16 | Cockroach Labs, Inc. | Methods and systems for transactional schema changes |
| CN115858622A (en) * | 2022-12-12 | 2023-03-28 | 浙江大学 | Automatic generation method of business data checking script |
| CN116401225A (en) * | 2023-03-28 | 2023-07-07 | 北京航空航天大学 | Distributed file system oriented to satellite cloud |
-
2023
- 2023-07-17 CN CN202310868595.1A patent/CN116610756B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593287A (en) * | 2013-10-30 | 2014-02-19 | 北京信息控制研究所 | Genetic-algorithm-based method for automatically generating data stream test cases |
| CN107103360A (en) * | 2017-03-31 | 2017-08-29 | 华南理工大学 | A kind of reliability application distribution distributed genetic algorithm based on mixed cloud |
| WO2019144046A1 (en) * | 2018-01-19 | 2019-07-25 | Hyperdyne, Inc. | Distributed high performance computing using distributed average consensus |
| CN109740037A (en) * | 2019-01-02 | 2019-05-10 | 山东省科学院情报研究所 | The distributed online real-time processing method of multi-source, isomery fluidised form big data and system |
| CN113449065A (en) * | 2021-06-29 | 2021-09-28 | 苏州链约科技有限公司 | Data deduplication-oriented decentralized storage method and storage device |
| US20230081900A1 (en) * | 2021-09-15 | 2023-03-16 | Cockroach Labs, Inc. | Methods and systems for transactional schema changes |
| CN113934374A (en) * | 2021-09-28 | 2022-01-14 | 北京理工大学 | Block chain multi-copy distribution and storage method based on genetic algorithm |
| CN114817402A (en) * | 2022-04-25 | 2022-07-29 | 山东浪潮科学研究院有限公司 | SQL execution optimization method of distributed database in multi-region deployment scene |
| CN115794854A (en) * | 2022-12-09 | 2023-03-14 | 华东师范大学 | Method for reading local linear consistency on copy based on Raft algorithm |
| CN115858622A (en) * | 2022-12-12 | 2023-03-28 | 浙江大学 | Automatic generation method of business data checking script |
| CN116401225A (en) * | 2023-03-28 | 2023-07-07 | 北京航空航天大学 | Distributed file system oriented to satellite cloud |
Non-Patent Citations (3)
| Title |
|---|
| CHEN DING; TING YAO; HONG JIANG; QIU CUI; LIU TANG; YIWEN ZHANG; JIGUANG WAN; ZHIHU TAN: "TriangleKV: Reducing Write Stalls and Write Amplification in LSM-Tree Based KV Stores With Triangle Container in NVM", IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, pages 4339 - 4352 * |
| 张晓丽;杨家海;孙晓晴;吴建平: "分布式云的研究进展综述", 软件学报, pages 2116 - 2132 * |
| 张静波;: "以并行遗传与蚁群算法为核心的分布式数据库优化", 通讯世界, no. 01, pages 274 - 275 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116610756B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837585B (en) | Multi-source heterogeneous data association query method and system | |
| CN110147407B (en) | Data processing method and device and database management server | |
| US20080263001A1 (en) | System and method for automating data partitioning in a parallel database | |
| EP3373158B1 (en) | Data storage method and coordinator node | |
| US11036709B2 (en) | Single-level, multi-dimension, hash-based table partitioning | |
| CN114398371A (en) | Multi-copy fragmentation method, device, equipment and storage medium for database cluster system | |
| WO2021231000A1 (en) | Managing snapshotting of a dataset using an ordered set of b+ trees | |
| Sadineni | Comparative study on skyline query processing techniques on big data | |
| CN111427931A (en) | Distributed query engine and method for querying relational database by using same | |
| CN111125199A (en) | Database access method and device and electronic equipment | |
| CN116610756B (en) | Distributed database self-adaptive copy selection method and device | |
| CN112632116B (en) | Method, system, equipment and medium for multi-node cluster scheduling of K-DB database | |
| CN116541427B (en) | Data query method, device, equipment and storage medium | |
| Doulkeridis et al. | On saying" enough already!" in mapreduce | |
| CN112699134A (en) | Distributed graph database storage and query method based on graph subdivision | |
| US10666728B1 (en) | System and method for maintaining data consistency across replicas in a cluster of nodes | |
| US20220215021A1 (en) | Data Query Method and Apparatus, Computing Device, and Storage Medium | |
| CN115114294A (en) | Self-adaption method and device of database storage mode and computer equipment | |
| US10824600B2 (en) | System and method for maintaining data consistency across replicas in a cluster of nodes using incremental validation | |
| Hartig et al. | A Main Memory Index Structure to Query Linked Data. | |
| US11423002B2 (en) | Multilevel partitioning of objects | |
| CN117591608B (en) | Cloud primary database data slicing method based on distributed hash | |
| CN116166755B (en) | Search engine database management method and device and search engine database | |
| CN111949439B (en) | Database-based data file updating method and device | |
| Arsov et al. | Prediction of Horizontal Data Partitioning Through Query Execution Cost Estimation |
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 |