CN110213326A - Expansion method, system, equipment and the storage medium of metadata node cluster - Google Patents
Expansion method, system, equipment and the storage medium of metadata node cluster Download PDFInfo
- Publication number
- CN110213326A CN110213326A CN201910303483.5A CN201910303483A CN110213326A CN 110213326 A CN110213326 A CN 110213326A CN 201910303483 A CN201910303483 A CN 201910303483A CN 110213326 A CN110213326 A CN 110213326A
- Authority
- CN
- China
- Prior art keywords
- metadata
- node
- service
- partition
- newly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/214—Database migration support
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/563—Data redirection of data network streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/06—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols the encryption apparatus using shift registers or memories for block-wise or stream coding, e.g. DES systems or RC4; Hash functions; Pseudorandom sequence generators
- H04L9/0643—Hash functions, e.g. MD5, SHA, HMAC or f9 MAC
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Power Engineering (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves expansion method, system, equipment and the storage mediums of a kind of metadata node cluster.Multiple Metadata Services are deployed in each metadata node in the metadata node cluster, each Metadata Service individually corresponds to a metadata partition, the described method includes: newly-increased metadata node, determine at least one metadata partition to be moved out for needing to move out in original metadata node, corresponding Metadata Service is disposed in newly-increased metadata node, the Metadata Service Metadata Service configuration consistency corresponding with metadata partition to be moved out disposed in newly-increased metadata node, metadata partition to be moved out is migrated into newly-increased metadata node.It can reduce the complexity of metadata node cluster dilatation using this method, improve the efficiency and effect of the dilatation of metadata node cluster.
Description
Technical field
This application involves technical field of data storage, more particularly to a kind of metadata node cluster expansion method, be
System, equipment and storage medium.
Background technique
In cloud storage system and distributed file system, memory node is the physical equipment for storing user data, first number
It is the physical equipment for storing metadata according to node, while metadata node is also responsible for carrying out pipe to the data of whole system and operation
Reason.Wherein, metadata can be understood as the data of the information such as index, filename, access authority comprising user data.
With being continuously increased for user data, metadata is also more and more, and the pressure that metadata node is born gradually increases
Greatly.It needs to carry out dilatation to the metadata node cluster formed by metadata nodes all in system in this case, to mention
Rise the performance of whole system.Currently, common dilatation way includes: newly-increased metadata node, by original first numbers all in system
It is combined according to the metadata set of node, then is distributed to all metadata nodes (including newly-increased metadata node and original first number
According to node) on;Alternatively, newly-increased metadata node, the metadata in the original metadata node in part in system is split, then
Metadata after fractionation is distributed in newly-increased metadata node.
However, needing to concentrate in together metadata when carrying out dilatation to metadata node cluster using aforesaid way
It is handled, it is also necessary to original metadata be split, realize that difficulty is larger, split process is also easier to that metadata occurs
Loss or entanglement.In addition, split process is time-consuming long when the amount of metadata for needing to split is bigger, system performance and its are influenced
His business is normally carried out.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide the expansion method of metadata node cluster a kind of, system,
Computer equipment and storage medium, can reduce the complexity of metadata node cluster dilatation, and improve metadata node cluster
The efficiency and effect of dilatation.
A kind of expansion method of metadata node cluster, each metadata node top in the metadata node cluster
There are multiple Metadata Services in administration, and each Metadata Service individually corresponds to a metadata partition, which comprises
Newly-increased metadata node;
Determine at least one metadata partition to be moved out for needing to move out in original metadata node;
Corresponding Metadata Service is disposed in newly-increased metadata node, the member disposed in newly-increased metadata node
Data service Metadata Service configuration consistency corresponding with metadata partition to be moved out;
The metadata partition to be moved out is moved in newly-increased metadata node.
At least one member to be moved out for needing to move out in the original metadata node of the determination in one of the embodiments,
The step of data subregion, comprising:
According in metadata node cluster after newly-increased metadata node metadata node sum and metadata partition sum,
At least one metadata partition to be moved out for needing to move out in original metadata node is determined according to load balancing principle.
In one of the embodiments, the method also includes:
When receiving when storing metadata, Hash calculation is carried out to the metadata to be stored, is determined described wait store
The Metadata Service that metadata should be stored in;
By in the data allocations to be stored to determining Metadata Service, incited somebody to action by the Metadata Service of the determination
The metadata to be stored is stored in the corresponding metadata partition of the Metadata Service.
Multiple members are deployed in each metadata node in the metadata node cluster in one of the embodiments,
Data service, using following implementations:
Metadata Service is directly disposed in each metadata node, each Metadata Service uses different IP address,
Data are stored in different paths.
Multiple members are deployed in each metadata node in the metadata node cluster in one of the embodiments,
Data service, using following implementations:
Metadata Service is disposed in each metadata node, each Metadata Service operates in different containers, often
A container has different IP address, and data are stored under different paths.
Multiple members are deployed in each metadata node in the metadata node cluster in one of the embodiments,
Data service, using following implementations:
Metadata Service is disposed in each metadata node, each Metadata Service operates in different virtual machines,
Each virtual machine has different IP address, and data are stored under different paths.
Each metadata node is equipped with a corresponding member in the metadata node cluster in one of the embodiments,
Data slave node, the metadata node forms hot standby group an of double-click as host node and the metadata slave node, described
Metadata slave node is in real time from host node synchrodata.
A kind of capacity-enlarging system of metadata node cluster, each metadata node top in the metadata node cluster
There are multiple Metadata Services in administration, and each Metadata Service individually corresponds to a metadata partition, the system comprises:
Node adding unit, for increasing metadata node newly;
Subregion determining module to be moved out needs at least one moved out to wait moving out first number for determining in original metadata node
According to subregion;
Service configuration module, for disposing corresponding Metadata Service in newly-increased metadata node, in newly-increased member
The Metadata Service disposed on back end Metadata Service configuration consistency corresponding with metadata partition to be moved out;And
Zoned migration unit, for migrating the metadata partition to be moved into newly-increased metadata node.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes step described in the expansion method of above-mentioned metadata node cluster when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Step described in the expansion method of above-mentioned metadata node cluster is realized when row.
It is every in metadata node cluster in the expansion method of above-mentioned metadata node cluster, system, equipment and storage medium
Multiple Metadata Services are deployed in a metadata node, each Metadata Service individually corresponds to a metadata partition, new
After increasing metadata node, the metadata partition to be moved out in original metadata node is migrated into newly-increased metadata node,
Without focusing on metadata, split without to metadata, the Data Migration amount of entire dilation process is few, reduces
The complexity of metadata node cluster dilatation reduces the probability that entanglement occurs for metadata in dilation process, improves metadata
The efficiency and effect of node cluster dilatation.
Detailed description of the invention
Fig. 1 is the applied environment figure of the expansion method of metadata node cluster in one embodiment;
Fig. 2 is the flow diagram of the expansion method of metadata node cluster in one embodiment;
Fig. 3 is the flow diagram of the expansion method of metadata node cluster in another embodiment;
Fig. 4 is that metadata partition migration to be moved out is former before in the expansion method of metadata node cluster in one embodiment
There is the topology example figure of metadata node;
Fig. 5 is the transition process of metadata partition to be moved out in the expansion method of metadata node cluster in one embodiment
Exemplary diagram;
Fig. 6 is in one embodiment in the expansion method of metadata node cluster after the migration of metadata partition to be moved out
The topology example figure of each metadata node;
Fig. 7 is the structural schematic diagram of storage system in one embodiment;
Fig. 8 is the structural schematic diagram of storage system in one embodiment;
Fig. 9 is the structural schematic diagram of storage system in one embodiment;
Figure 10 is the structural block diagram of the capacity-enlarging system of metadata node cluster in one embodiment;And
Figure 11 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
The expansion method of metadata node cluster provided by the present application, can be applied in application environment as shown in Figure 1.
Wherein, server 140 form server cluster, can to user data carry out distributed storage, terminal 102 by network with by taking
The server cluster that business device 104 forms is communicated by network, to be written or read data.Wherein, terminal 102 can with but not
It is limited to be various personal computers, laptop, smart phone, tablet computer and portable wearable device.
In one embodiment, as shown in Fig. 2, providing a kind of expansion method of metadata node cluster, in this way
Applied to being illustrated for the server cluster in Fig. 1, comprising the following steps:
Step 202, metadata node is increased newly.
Specifically, metadata node is the server for storing metadata, meta data server (MetaData can be described as
Server, abbreviation MDS).In the storage system where metadata node, metadata node cluster includes all metadata sections
Point, multiple Metadata Services are deployed in each metadata node, and each Metadata Service individually corresponds to a metadata partition.
Wherein, the metadata stored in all metadata partitions constitutes the metadata of entire storage system, and Metadata Service is to first number
It is managed the service routine of (or service) according to subregion, such as metadata storage is carried out to metadata partition, to reading metadata
The request of metadata is responded in subregion.
Specifically, when storage system needs the metadata stored to increase where metadata node cluster, or when original
When the load pressure of metadata node is excessively high, metadata node is increased newly, i.e. increase meta data server.
Step 204, at least one metadata partition to be moved out for needing to move out in original metadata node is determined.
Specifically, metadata node cluster includes original metadata node and newly-increased first number after newly-increased metadata node
According to node.Metadata Service, each Metadata Service and individually a corresponding metadata are deployed under original metadata node
Subregion, i.e. Metadata Service and metadata partition are the binding relationship mapped one by one.And not yet portion in newly-increased metadata node
Metadata Service is affixed one's name to, also unallocated metadata.In the dilation process of metadata node cluster, the purpose of metadata node is increased newly
It is to mitigate the load pressure of original metadata node, while improves the metadata amount of storage of metadata node cluster.Therefore, exist
After newly-increased metadata node, at least one of original metadata node metadata partition to be moved out, metadata to be moved out are determined
The metadata partition that subregion needs to move out from original metadata node.
Step 206, corresponding Metadata Service is disposed in newly-increased metadata node, in newly-increased metadata node
The Metadata Service of deployment Metadata Service configuration consistency corresponding with metadata partition to be moved out.
Specifically, determine in original metadata node behind metadata partition of moving out, in newly-increased metadata node
Upper to dispose corresponding Metadata Service, the Metadata Service disposed in newly-increased metadata node is used to manage wait first number of moving out
According to subregion.The Metadata Service disposed in newly-increased metadata node, with metadata partition to be moved out in original metadata section
Corresponding Metadata Service configuration consistency on point, thus guarantee the consistency of metadata partition migration front and back Metadata Service,
Avoid metadata node cluster that data entanglement occurs.Wherein, Metadata Service configuration consistency includes metadata partition information (first number
According to the file size of subregion, filename, store path etc.) it is consistent consistent with the operating parameter of Metadata Service.
When the number of newly-increased metadata node is two or more, will metadata partition be moved out distribute to it is newly-increased
Metadata node, deployment is used to manage the member for the metadata partition to be moved out itself being assigned in newly-increased metadata node
Data service.
Step 208, metadata partition to be moved out is migrated into newly-increased metadata node.
Specifically, after disposing good corresponding Metadata Service in newly-increased metadata node, it will metadata be moved out point
Area is stored into newly-increased metadata node, realizes metadata partition to be moved out from original metadata node to newly-increased metadata section
The dilatation of metadata node cluster is completed in the migration of point.
In another embodiment, as shown in figure 3, a kind of expansion method of metadata node cluster is provided, with the party
Method is applied to be illustrated for the server cluster in Fig. 1, comprising the following steps:
Step 301, metadata node is increased newly.
Specifically, newly-increased metadata node, i.e., increase metadata clothes in the storage system where original metadata node
Business device.In the storage system where metadata node, multiple Metadata Services, Mei Geyuan are deployed in each metadata node
Data service and individually a corresponding metadata partition.
Step 302, according to the metadata node sum and metadata in metadata node cluster after newly-increased metadata node
Subregion sum determines at least one metadata to be moved out point for needing to move out in original metadata node according to load balancing principle
Area.
Specifically, after newly-increased metadata node, metadata section in metadata node cluster after the newly-increased metadata node of acquisition
The sum of point and the sum of metadata partition, according to the metadata node sum, metadata partition sum and load balancing obtained
Principle determines the metadata partition to be moved out for needing to move out in original metadata node, thus to metadata node cluster into
While row dilatation, guarantee the equilibrium for the metadata partition quantity that metadata node is loaded, and then improve metadata node collection
The capacity enlargement effect of group.
In one embodiment, it is determined according to metadata node sum, metadata partition sum and load balancing principle
In original metadata node wait move out metadata partition when, calculate single metadata node on metadata partition average
Amount, when metadata partition quantity is more than the par in original metadata node, retaining in original metadata node should
Remaining metadata partition is set metadata partition to be moved out by par metadata partition.Further, it is also possible to foundation
The load capacity of original metadata node chooses metadata partition to be moved out, so that the present load of original metadata node is in member
Back end loads in tolerance range.
Step 303, corresponding Metadata Service is disposed in newly-increased metadata node, in newly-increased metadata node
The Metadata Service of deployment Metadata Service configuration consistency corresponding with metadata partition to be moved out.
Specifically, determine in original metadata node behind metadata partition of moving out, in newly-increased metadata node
Upper to dispose corresponding Metadata Service, the Metadata Service disposed in newly-increased metadata node is used to manage wait first number of moving out
According to subregion.The Metadata Service disposed in newly-increased metadata node, with metadata partition to be moved out in original metadata section
Corresponding Metadata Service configuration consistency on point, thus guarantee the consistency of metadata partition migration front and back Metadata Service,
Avoid metadata node cluster that data entanglement occurs.
When the number of newly-increased metadata node is two or more, will metadata partition be moved out distribute to it is newly-increased
Metadata node, deployment is used to manage the member for the metadata partition to be moved out itself being assigned in newly-increased metadata node
Data service.
Step 304, metadata partition to be moved out is moved in newly-increased metadata node.
It specifically, will metadata partition be moved out after newly-increased metadata node has disposed corresponding Metadata Service
It stores in newly-increased metadata node, realizes the migration of metadata partition to be moved out, be completed at the same time metadata node cluster
Dilatation.
As illustratively, in Fig. 4, Fig. 5 and Fig. 6, original metadata node is metadata section in metadata node cluster
Point 1 and metadata node 2, metadata node 1 are deployed with Metadata Service 1, Metadata Service 2 and Metadata Service 3, metadata
Node 2 is deployed with Metadata Service 4, Metadata Service 5 and Metadata Service 6.Increase metadata newly in metadata node cluster
Node 3, the sum of metadata node is 3 in metadata node cluster at this time and the sum of metadata partition is 6, equal according to load
Weigh principle, and each metadata node should be disposed there are two Metadata Service, be needed in metadata node 1 and metadata node 2
A metadata partition to be moved out is selected respectively.Metadata partition 3 is selected in metadata node 1 as metadata to be moved out point
Area selects metadata partition 6 in metadata node 2 and is used as metadata partition to be moved out, since metadata partition 3 is in metadata
Metadata Service 3 is corresponded in node 1, metadata partition 6 is in the corresponding Metadata Service 6 of metadata node 2, in metadata node 3
The Metadata Service with 6 configuration consistency of Metadata Service 3 and Metadata Service respectively is disposed, in order to make it easy to understand, first number in Fig. 5
It is equally named as Metadata Service 3 and Metadata Service 6 according to the Metadata Service disposed in node 3, by metadata partition 3, member
Data subregion 6 migrates Metadata Service 3 and Metadata Service 6 into metadata node 3 respectively, completes to metadata node collection
The dilatation of group.
In one embodiment, it when the storage system where metadata cluster receives when storing metadata, treats and deposits
It stores up metadata and carries out Hash calculation, the result according to Hash calculation determines the Metadata Service that metadata to be stored should be stored in, will
In data allocations to be stored to determining Metadata Service, metadata to be stored is stored in by determining Metadata Service
In the corresponding metadata partition of Metadata Service.Wherein, the default key assignments (text of metadata such as to be stored of storage metadata is treated
Part name, pathname or file identification etc.) Hash calculation is carried out, realize the partitioned storage of metadata to be stored to difference.
In one embodiment, the storage system where metadata cluster further includes agent node, agent node be for
The server being managed is read to the write-in of user data and metadata, agency service is deployed in agent node, is acted on behalf of
Service is the service routine for realizing agent node function.It is received when storing metadata in storage system, agent node
In agency service treat storage metadata and carry out Hash calculation, determine the corresponding Metadata Service of metadata to be stored.First number
According to before and after node cluster dilatation, the Metadata Service configuration consistency of metadata partition to be migrated, in metadata partition to be migrated
Metadata is also consistent, therefore without changing the Hash rule for carrying out subregion to metadata in dilation process, agency service is not yet
It needs to make any modification, significantly reduces the complexity of metadata node cluster dilatation, improve efficiency.
In one embodiment, each metadata node is when disposing Metadata Service in metadata node cluster, each
Metadata Service uses different IP address, and data are stored in different paths, are disposed in each metadata node with realizing
There are multiple Metadata Services and each Metadata Service individually corresponds to a metadata partition.Wherein, the number in Metadata Service
According to the operating parameter including metadata partition information and Metadata Service.
In one embodiment, each Metadata Service is stored in different paths using different IP address and data,
It can be realized by using the mode of container or virtual machine, to improve the deployment effect of Metadata Service.Specifically, each metadata
For service operation in different containers, each container has different IP address, and data are stored under different paths;Alternatively,
Each Metadata Service operates in different virtual machines, and each virtual machine has different IP address, and data are stored in difference
Path.
In one embodiment, each metadata node is equipped with a corresponding metadata slave node, and metadata node is made
A two-node cluster hot backup group is formed for host node and corresponding metadata slave node, metadata slave node is from master in two-node cluster hot backup group
Synchrodata in node, any node in metadata node or metadata slave node breaks down, and (such as data can not be read
Take or be written, data read error misses) when, data support can be obtained from another node in two-node cluster hot backup group at any time, thus
Effectively improve the stability and reliability of storage system.
In the expansion method of above-mentioned metadata node cluster, multiple Metadata Services are deployed in metadata node, often
A Metadata Service individually correspond to a metadata partition, according to load balancing principle determine in original metadata node to
It moves out metadata partition, metadata partition to be moved out is migrated into the Metadata Service of newly-increased metadata node, thus
Without being split to metadata in dilation process, without the metadata assembled in multiple original metadata nodes, effectively
The complexity for reducing the dilatation of metadata node cluster reduces the probability that entanglement occurs for metadata in dilation process, improves first number
According to the efficiency and effect of node cluster dilatation.
It should be understood that although each step in the flow chart of Fig. 2~3 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2~3 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can replace at least part of the sub-step or stage of other steps or other steps
Ground executes.
In one embodiment, as shown in fig. 7, providing a kind of storage system, which includes memory node and member
Back end, memory node are the server for storing user data, and metadata node is the member for storing user data
The server of data.Storage service is deployed in memory node, storage service is used to carry out storage management to user data,
Multiple Metadata Services are deployed in metadata node, Metadata Service is used to carry out metadata storage management, each member number
A metadata partition is individually corresponded to according to service.Wherein, m indicates the number of metadata node in Fig. 7, and n indicates memory node
Number.
Specifically, each metadata node, when disposing Metadata Service, each Metadata Service is using different IP
Location, and data are stored in different paths, and multiple Metadata Services and each member are deployed in each metadata node to realize
Data service individually corresponds to the system structure of a metadata partition.Wherein, the data in Metadata Service include metadata point
The operating parameter of area's information and Metadata Service.
In an alternative embodiment, each Metadata Service is stored in difference using different IP address and data
Path, can be realized by using the mode of container or virtual machine, to improve the deployment effect of Metadata Service.Specifically, every
A Metadata Service operates in different containers, and each container has different IP address, and data are stored in different paths
Under;Alternatively, each Metadata Service operates in different virtual machines, each virtual machine has different IP address, and data are deposited
It is placed on different paths.
Specifically, treating storage metadata when storage system receives when storing metadata and carrying out Hash calculation, determine
The Metadata Service that metadata to be stored should be stored in, by data allocations to be stored to determining Metadata Service, by true
Metadata to be stored is stored in the corresponding metadata partition of Metadata Service by fixed Metadata Service, completes writing for metadata
Enter.Wherein, the default key assignments (filename, pathname or the file identification of metadata such as to be stored) of storage metadata is treated
Carry out Hash calculation.
Specifically, increasing member newly within the storage system when expanding the metadata node cluster in the storage system
Back end, and at least one metadata partition to be moved out moved out is needed in original metadata node in determining storage system,
Corresponding Metadata Service is disposed in newly-increased metadata node, and metadata partition to be moved out is moved to newly-increased metadata section
In point, wherein the Metadata Service disposed in newly-increased metadata node is in metadata partition to be moved out in original metadata section
Corresponding Metadata Service configuration consistency in point.The expansion process of metadata node cluster can refer to the above method in storage system
Each step of embodiment, details are not described herein.
In an alternative embodiment, as shown in figure 8, storage system further includes agent node, agent node be for
The server being managed is read to the write-in of user data and metadata, agency service is deployed in agent node, is acted on behalf of
Service is used to realize the function of agent node.It is received when storing metadata in storage system, storage is treated by agent node
Metadata carries out Hash calculation, determines the corresponding Metadata Service of metadata to be stored.Before and after the dilatation of metadata node cluster, to
The Metadata Service configuration consistency of metadata partition is migrated, the metadata in metadata partition to be migrated is also consistent, therefore is expanding
Without changing the Hash rule for carrying out subregion to metadata during holding, agency service does not need to make any modification yet, effectively
The complexity for reducing metadata node cluster dilatation, improves efficiency.Wherein, in Fig. 8 k indicate agent node number.
Specifically, the number of memory node, metadata node and agent node, can be designed according to the actual situation,
This is not restricted.
In one embodiment, as shown in figure 9, each metadata node is equipped with a corresponding metadata slave node, member
Back end forms a two-node cluster hot backup group, the metadata in two-node cluster hot backup group with corresponding metadata slave node as host node
Slave node synchrodata from host node, any node in metadata node or metadata slave node break down (such as
Data can not read or be written, data read error misses) when, can data be obtained from another node in two-node cluster hot backup group at any time
It supports, to effectively improve the stability and reliability of storage system.
In one embodiment, as shown in Figure 10, a kind of capacity-enlarging system 1000 of metadata node cluster is provided, is wrapped
It includes: node adding unit 1002, subregion determination unit 1004 to be moved out, service arrangement unit 1006 and zoned migration unit
1008, in which:
Node adding unit 1002, for increasing metadata node newly;
Subregion determination unit 1004 to be moved out, for determining at least one member to be moved out moved out in original metadata node
Data subregion;
Service arrangement unit 1006, for disposing corresponding Metadata Service in newly-increased metadata node, newly-increased
Metadata node on the Metadata Service Metadata Service configuration consistency corresponding with metadata partition to be moved out disposed;With
And
Zoned migration unit 1008, for migrating metadata partition to be moved into newly-increased metadata node.
In one embodiment, subregion determination unit 1004 to be moved out includes:
Load balancing determination unit, for according to the metadata node in metadata node cluster after newly-increased metadata node
Sum and metadata partition sum, determining according to load balancing principle needs at least one moved out to wait moving in original metadata node
Metadata partition out.
In one embodiment, the capacity-enlarging system 1000 of metadata node cluster further include:
Hash calculation unit carries out Hash calculation for when receiving when storing metadata, treating storage metadata, really
The Metadata Service that fixed metadata to be stored should be stored in;
Metadata storage unit, for will data allocations be stored to determining Metadata Service, by determining
Metadata to be stored is stored in the corresponding metadata partition of Metadata Service by Metadata Service.
In one embodiment, the capacity-enlarging system 1000 of metadata node cluster further include:
Metadata Service deployment unit, for directly disposing Metadata Service, each member number in each metadata node
Different IP address is used according to service, data are stored in different paths.
In one embodiment, the capacity-enlarging system 1000 of metadata node cluster further include:
Container deployment unit, for disposing Metadata Service, each Metadata Service operation in each metadata node
In different containers, each container has different IP address, and data are stored under different paths.
In one embodiment, the capacity-enlarging system 1000 of metadata node cluster further include:
Deploying virtual machine unit, for disposing Metadata Service, each Metadata Service fortune in each metadata node
For row in different virtual machines, each virtual machine has different IP address, and data are stored under different paths.
In one embodiment, each in metadata node cluster in the capacity-enlarging system 1000 of metadata node cluster
Metadata node is equipped with a corresponding metadata slave node, and metadata node is as host node and metadata slave node composition one
A two-node cluster hot backup group, metadata slave node is in real time from host node synchrodata.
The specific restriction of capacity-enlarging system about above-mentioned metadata node cluster may refer to above for metadata section
The restriction of the expansion method of point cluster, details are not described herein.Each unit in the capacity-enlarging system of above-mentioned metadata node cluster
It can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each unit can be embedded in the form of hardware or independently of
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to locate
It manages device and calls the corresponding operation of the above modules of execution.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in figure 11.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the metadata etc. of user data and user data.The network interface of the computer equipment is used for
It is communicated with external terminal by network connection.To realize a kind of metadata node collection when the computer program is executed by processor
The expansion method of group.
It will be understood by those skilled in the art that structure shown in Figure 11, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Newly-increased metadata node;
Determine at least one metadata partition to be moved out for needing to move out in original metadata node;
Corresponding Metadata Service is disposed in newly-increased metadata node, the member disposed in newly-increased metadata node
Data service Metadata Service configuration consistency corresponding with metadata partition to be moved out;
Metadata partition to be moved out is moved in newly-increased metadata node.
In one embodiment, it is also performed the steps of when which executes computer program
According in metadata node cluster after newly-increased metadata node metadata node sum and metadata partition sum,
At least one metadata partition to be moved out for needing to move out in original metadata node is determined according to load balancing principle.
In one embodiment, it is also performed the steps of when which executes computer program
When receiving when storing metadata, treats storage metadata and carry out Hash calculation, determine that metadata to be stored is answered
The Metadata Service of deposit;
It, will member be stored by determining Metadata Service by data allocations to be stored to determining Metadata Service
Data are stored in the corresponding metadata partition of Metadata Service.
In one embodiment, it is also performed the steps of when which executes computer program
Metadata Service is directly disposed in each metadata node, each Metadata Service uses different IP address,
Data are stored in different paths.
In one embodiment, it is also performed the steps of when which executes computer program
Metadata Service is disposed in each metadata node, each Metadata Service operates in different containers, often
A container has different IP address, and data are stored under different paths.
In one embodiment, it is also performed the steps of when which executes computer program
Metadata Service is disposed in each metadata node, each Metadata Service operates in different virtual machines,
Each virtual machine has different IP address, and data are stored under different paths.
In one embodiment, each metadata node is equipped with the standby section of a corresponding metadata in metadata node cluster
Point, metadata node form a two-node cluster hot backup group as host node and metadata slave node, and metadata slave node is in real time from master
Node synchrodata.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Newly-increased metadata node;
Determine at least one metadata partition to be moved out for needing to move out in original metadata node;
Corresponding Metadata Service is disposed in newly-increased metadata node, the member disposed in newly-increased metadata node
Data service Metadata Service configuration consistency corresponding with metadata partition to be moved out;
Metadata partition to be moved out is moved in newly-increased metadata node.
In one embodiment, it is also performed the steps of when computer program is executed by processor
According in metadata node cluster after newly-increased metadata node metadata node sum and metadata partition sum,
At least one metadata partition to be moved out for needing to move out in original metadata node is determined according to load balancing principle.
In one embodiment, it is also performed the steps of when computer program is executed by processor
When receiving when storing metadata, treats storage metadata and carry out Hash calculation, determine that metadata to be stored is answered
The Metadata Service of deposit;
It, will member be stored by determining Metadata Service by data allocations to be stored to determining Metadata Service
Data are stored in the corresponding metadata partition of Metadata Service.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Metadata Service is directly disposed in each metadata node, each Metadata Service uses different IP address,
Data are stored in different paths.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Metadata Service is disposed in each metadata node, each Metadata Service operates in different containers, often
A container has different IP address, and data are stored under different paths.In one embodiment, computer program is processed
Device also performs the steps of when executing
Metadata Service is disposed in each metadata node, each Metadata Service operates in different virtual machines,
Each virtual machine has different IP address, and data are stored under different paths.
In one embodiment, each metadata node is equipped with the standby section of a corresponding metadata in metadata node cluster
Point, metadata node form a two-node cluster hot backup group as host node and metadata slave node, and metadata slave node is in real time from master
Node synchrodata.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of expansion method of metadata node cluster, which is characterized in that each of described metadata node cluster member number
According to multiple Metadata Services are deployed on node, each Metadata Service individually corresponds to a metadata partition;The side
Method includes:
Newly-increased metadata node;
Determine at least one metadata partition to be moved out for needing to move out in original metadata node;
Corresponding Metadata Service is disposed in newly-increased metadata node, the metadata disposed in newly-increased metadata node
Service Metadata Service configuration consistency corresponding with metadata partition to be moved out;
The metadata partition to be moved out is moved in newly-increased metadata node.
2. the method as described in claim 1, which is characterized in that need move out at least one in the original metadata node of determination
The step of a metadata partition to be moved out, comprising:
According to the metadata node sum and metadata partition sum in metadata node cluster after newly-increased metadata node, foundation
Load balancing principle determines at least one metadata partition to be moved out for needing to move out in original metadata node.
3. the method as described in claim 1, which is characterized in that the method also includes:
When receiving when storing metadata, Hash calculation is carried out to the metadata to be stored, is determined described wait store first number
According to the Metadata Service that should be stored in;
It, will be described by the Metadata Service of the determination by the data allocations to be stored to determining Metadata Service
Metadata to be stored is stored in the corresponding metadata partition of the Metadata Service.
4. the method according to claim 1, wherein each metadata node in the metadata node cluster
On be deployed with multiple Metadata Services, using following implementations:
Metadata Service is directly disposed in each metadata node, each Metadata Service uses different IP address, data
It is stored in different paths.
5. the method according to claim 1, wherein each metadata node in the metadata node cluster
On be deployed with multiple Metadata Services, using following implementations:
Metadata Service is disposed in each metadata node, each Metadata Service operates in different containers, Mei Gerong
Device has different IP address, and data are stored under different paths.
6. the method according to claim 1, wherein each metadata node in the metadata node cluster
On be deployed with multiple Metadata Services, using following implementations:
Metadata Service is disposed in each metadata node, each Metadata Service operates in different virtual machines, each
Virtual machine has different IP address, and data are stored under different paths.
7. the method as described in claim 1, which is characterized in that each metadata node is equipped in the metadata node cluster
A corresponding metadata slave node, the metadata node form a two-shipper as host node and the metadata slave node
Hot standby group, the metadata slave node is in real time from host node synchrodata.
8. a kind of capacity-enlarging system of metadata node cluster, which is characterized in that each of described metadata node cluster member number
According to multiple Metadata Services are deployed on node, each Metadata Service individually corresponds to a metadata partition, the system
System includes:
Node adding unit, for increasing metadata node newly;
Subregion determination unit to be moved out, for determining at least one metadata to be moved out for needing to move out in original metadata node point
Area;And
Service arrangement unit, for disposing corresponding Metadata Service in newly-increased metadata node, in newly-increased metadata
The Metadata Service disposed on node Metadata Service configuration consistency corresponding with metadata partition to be moved out;And
Zoned migration unit, for migrating the metadata partition to be moved into newly-increased metadata node.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910303483.5A CN110213326B (en) | 2019-04-15 | 2019-04-15 | Method, system, equipment and storage medium for capacity expansion of metadata node cluster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910303483.5A CN110213326B (en) | 2019-04-15 | 2019-04-15 | Method, system, equipment and storage medium for capacity expansion of metadata node cluster |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110213326A true CN110213326A (en) | 2019-09-06 |
CN110213326B CN110213326B (en) | 2022-03-01 |
Family
ID=67785342
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910303483.5A Active CN110213326B (en) | 2019-04-15 | 2019-04-15 | Method, system, equipment and storage medium for capacity expansion of metadata node cluster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110213326B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111723148A (en) * | 2020-04-10 | 2020-09-29 | 浙江大华技术股份有限公司 | Data storage method and device, storage medium and electronic device |
CN113467722A (en) * | 2021-07-26 | 2021-10-01 | 浙江大华技术股份有限公司 | Data migration method and device of distributed storage system |
CN113553314A (en) * | 2021-07-16 | 2021-10-26 | 北京天融信网络安全技术有限公司 | Service processing method, device, equipment and medium of super-convergence system |
CN114979162A (en) * | 2022-05-16 | 2022-08-30 | 中国工商银行股份有限公司 | Node deployment method and network system |
CN117348975A (en) * | 2023-12-05 | 2024-01-05 | 中电云计算技术有限公司 | Cluster deployment method, device, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354726A (en) * | 2008-09-17 | 2009-01-28 | 中国科学院计算技术研究所 | Method for managing memory metadata of cluster file system |
US20110289049A1 (en) * | 2010-05-19 | 2011-11-24 | Microsoft Corporation | Scaleable fault-tolerant metadata service |
CN103229487A (en) * | 2012-12-27 | 2013-07-31 | 华为技术有限公司 | Partition balance method, device and server in distributed storage system |
CN105468473A (en) * | 2014-07-16 | 2016-04-06 | 北京奇虎科技有限公司 | Data migration method and data migration apparatus |
CN107395721A (en) * | 2017-07-20 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and system of metadata cluster dilatation |
CN107528924A (en) * | 2017-10-09 | 2017-12-29 | 郑州云海信息技术有限公司 | A kind of distributed type assemblies Metadata Service dispositions method and system |
-
2019
- 2019-04-15 CN CN201910303483.5A patent/CN110213326B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354726A (en) * | 2008-09-17 | 2009-01-28 | 中国科学院计算技术研究所 | Method for managing memory metadata of cluster file system |
US20110289049A1 (en) * | 2010-05-19 | 2011-11-24 | Microsoft Corporation | Scaleable fault-tolerant metadata service |
CN103229487A (en) * | 2012-12-27 | 2013-07-31 | 华为技术有限公司 | Partition balance method, device and server in distributed storage system |
CN105468473A (en) * | 2014-07-16 | 2016-04-06 | 北京奇虎科技有限公司 | Data migration method and data migration apparatus |
CN107395721A (en) * | 2017-07-20 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and system of metadata cluster dilatation |
CN107528924A (en) * | 2017-10-09 | 2017-12-29 | 郑州云海信息技术有限公司 | A kind of distributed type assemblies Metadata Service dispositions method and system |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111723148A (en) * | 2020-04-10 | 2020-09-29 | 浙江大华技术股份有限公司 | Data storage method and device, storage medium and electronic device |
CN113553314A (en) * | 2021-07-16 | 2021-10-26 | 北京天融信网络安全技术有限公司 | Service processing method, device, equipment and medium of super-convergence system |
CN113467722A (en) * | 2021-07-26 | 2021-10-01 | 浙江大华技术股份有限公司 | Data migration method and device of distributed storage system |
CN113467722B (en) * | 2021-07-26 | 2024-04-30 | 浙江大华技术股份有限公司 | Data migration method and device of distributed storage system |
CN114979162A (en) * | 2022-05-16 | 2022-08-30 | 中国工商银行股份有限公司 | Node deployment method and network system |
CN114979162B (en) * | 2022-05-16 | 2024-02-09 | 中国工商银行股份有限公司 | Node deployment method and network system |
CN117348975A (en) * | 2023-12-05 | 2024-01-05 | 中电云计算技术有限公司 | Cluster deployment method, device, equipment and storage medium |
CN117348975B (en) * | 2023-12-05 | 2024-03-15 | 中电云计算技术有限公司 | Cluster deployment method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110213326B (en) | 2022-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110213326A (en) | Expansion method, system, equipment and the storage medium of metadata node cluster | |
CN110535969B (en) | Data storage method, device, storage medium and equipment based on block chain network | |
US20180150640A1 (en) | Policy aware unified file system | |
CN107247619B (en) | Live migration of virtual machine method, apparatus, system, storage medium and equipment | |
CN102158540A (en) | System and method for realizing distributed database | |
CN105515864A (en) | Container resource adaptive adjustment method and container resource adaptive adjustment system | |
CN110188084A (en) | A kind of distributed file storage system and file memory method | |
CN102117287A (en) | Distributed file system access method, a metadata server and client side | |
CN105701219A (en) | Distributed cache implementation method | |
WO2017050064A1 (en) | Memory management method and device for shared memory database | |
CN109271376A (en) | Database upgrade method, apparatus, equipment and storage medium | |
CN104572242A (en) | Method and device for expanding disk space of virtual machine and virtual machine system | |
CN104461706B (en) | A kind of method and multiprocessing device that shared global variable is shared | |
JP2015528957A (en) | Distributed file system, file access method, and client device | |
CN111198845A (en) | Data migration method, readable storage medium and computing device | |
US11138178B2 (en) | Separation of computation from storage in database for better elasticity | |
CN107943412B (en) | Method, device and system for splitting partition and deleting data file in partition | |
CN113434470B (en) | Data distribution method and device and electronic equipment | |
CN104517067A (en) | Method, device and system for data access | |
CN107943615B (en) | Data processing method and system based on distributed cluster | |
US9037762B2 (en) | Balancing data distribution in a fault-tolerant storage system based on the movements of the replicated copies of data | |
CN115982101B (en) | Machine room data migration method and device based on multi-machine room copy placement strategy | |
CN104484136A (en) | Method capable of supporting high-concurrency memory data | |
CN115134238B (en) | Business system publishing method, device, computer equipment and storage medium | |
CN110008140A (en) | EMS memory management process, device, computer equipment and storage medium |
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 |