CN116132460A - Distributed storage system based on server role and type division - Google Patents
Distributed storage system based on server role and type division Download PDFInfo
- Publication number
- CN116132460A CN116132460A CN202211697223.9A CN202211697223A CN116132460A CN 116132460 A CN116132460 A CN 116132460A CN 202211697223 A CN202211697223 A CN 202211697223A CN 116132460 A CN116132460 A CN 116132460A
- Authority
- CN
- China
- Prior art keywords
- storage
- server
- role
- gateway
- servers
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003993 interaction Effects 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000000638 solvent extraction Methods 0.000 claims description 10
- 230000008901 benefit Effects 0.000 abstract description 4
- 210000001503 joint Anatomy 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000002955 isolation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a distributed storage system based on server role and type division, which comprises: the storage servers are used for managing storage space, mon, mgr and osd services are operated on the storage servers, and the storage servers are divided into a plurality of storage pools in advance; the plurality of gateway servers are used for providing library functions and realizing data interaction when being in butt joint with the front-end application node, the plurality of gateway servers are matched with the plurality of storage pools, the plurality of storage servers and the plurality of gateway servers form a server cluster, and at least one of the following roles is provided for any server in the server cluster: management roles, monitor roles, block storage gateway roles, object storage gateway roles, file storage gateway roles. Compared with the prior art, the invention has the advantages of easy maintenance and management, etc.
Description
Technical Field
The invention relates to the field of cloud platform storage, in particular to a distributed storage system supporting multiple protocols.
Background
In recent years, with the proliferation of storage requirements and the increasing unstructured data, the limitations of conventional storage architectures have been increasingly highlighted. The capacity of the front-end controller for providing services to the outside is limited, and the capacity of the storage device for providing services to the outside cannot be effectively improved by longitudinally expanding the number of the magnetic disks. At the same time, the front-end controller has very limited lateral expansion capability. In addition, because the software and the hardware are tightly coupled, the unified management and the elastic scheduling of resources cannot be realized due to the limiting factors such as non-unified management interfaces, and the phenomenon of lower storage utilization rate can be brought.
The distributed storage adopts a distributed system architecture, and a plurality of storage servers are utilized to share load, so that the distributed storage has a plurality of advantages compared with the traditional storage architecture. Firstly, the distributed storage can generally manage the read cache and the write cache efficiently, support automatic hierarchical storage, carry out loose coupling link through a network, allow the separate deployment of high-speed storage and low-speed storage, and play the advantage of hierarchical storage to the best in unpredictable business environments or agile application scenes. Second, unlike conventional storage architectures that use RAID modes to ensure reliability of data, distributed storage employs a multiple copy mechanism. Before storing the data, the distributed storage segments the data, and the segmented data is stored on the cluster nodes according to a certain rule. In order to ensure consistency among multiple data copies, the distributed storage generally adopts a strong consistency technology of writing one copy and reading multiple copies, and different requirements of tenants on reliability are met by using modes of mirroring, stripe, distributed verification and the like. When the data reading fails, the system can read the data from other copies and re-write the data into the copies for recovery, so that the total number of the copies is ensured to be fixed; when the data is in an inconsistent state for a long time, the system can automatically reconstruct and restore the data, and meanwhile, the tenant can set the bandwidth rule of the data restoration, so that the influence on the service is minimized. Thanks to a reasonable distributed architecture, distributed storage can be predicted and flexibly expand computing, storage capacity and performance.
The distributed storage architecture not only improves the reliability, availability and access efficiency of the system, but also is easy to expand, minimizes the instability factors introduced by general hardware, and gradually becomes the dominant storage device of a future data center. However, the server type and function in the current distributed storage architecture are mixed, and maintenance and management are not easy.
In summary, a distributed storage system is lacking currently, so as to solve the problems of mixed server types and functions and difficult maintenance and management in the existing storage system.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a distributed storage system based on server role and type division, so as to solve or partially solve the problem that the existing distributed storage architecture lacks the division of servers and is difficult to maintain and manage.
The aim of the invention can be achieved by the following technical scheme:
the invention provides a distributed storage system based on server role and type division, which comprises:
the storage servers are used for managing storage space, mon, mgr and osd services are operated on the storage servers, and the storage servers are divided into a plurality of storage pools in advance;
a plurality of gateway servers for providing librbd functionality and enabling data interaction when interfacing with the front-end application node, the plurality of gateway servers being matched with the plurality of storage pools,
the plurality of storage servers and the plurality of gateway servers form a server cluster, and at least one of the following roles is provided for any server in the server cluster:
a management role, wherein a server with the management role is used for managing the server cluster;
the monitoring role, the server with the monitoring role is used for maintaining the state of the server cluster through collecting, updating and releasing cluster information;
a block storage gateway role, a server having the block storage gateway role for providing a SCSI-based protocol interface;
an object storage gateway role, the server having the object storage gateway role for providing an S3 protocol based access interface;
and the server with the file storage gateway role is used for providing file service for the server cluster.
As an optimal technical scheme, each storage server is provided with at least one hard disk.
As an preferable technical scheme, the plurality of gateway servers are in one-to-one butt joint with the plurality of storage pools.
Preferably, the plurality of storage pools includes a block storage pool, a file storage pool and a gateway storage pool.
According to the preferable technical scheme, after an external request is received, a Map copy of the server cluster is obtained through a server with the monitoring role, and the determination of a target storage server is realized according to the Map copy, so that data interaction is realized.
As a preferable technical scheme, the storage servers realize the management of the storage space by running the Pool component.
As a preferable technical scheme, a mon service is operated on the server with the monitoring role.
As a preferable technical scheme, a Block component is operated on the server with the Block storage gateway role.
As a preferred solution, the server having the Object storage gateway role runs with an Object component.
As a preferable technical scheme, a File component is operated on the server with the File storage gateway role.
Compared with the prior art, the invention has the following advantages:
(1) The server is divided into a storage server and a gateway server based on server types, the storage server is divided into a plurality of storage pools in advance according to service requirements and is in butt joint with the gateway server, each server has at least one role of management roles, monitoring roles, block storage gateway roles, object storage gateway roles and file storage gateway roles, the cluster unified management and server multi-role configuration can be realized based on the server roles and types, and the server is convenient to maintain and manage in a targeted manner, so that the problem that the maintenance and management are difficult due to the fact that the existing distributed storage architecture lacks of the division of the server is solved or partially solved.
(2) According to the front-end service demand, the clusters respectively provide block, file and object storage, simultaneously support a plurality of protocols such as rbd, nfs, cifs, s3 and the like, and meanwhile, the multi-cabinet deployment enables the system to be safer and more reliable, so that the demands of different application scenes can be met, and the isolation of data traffic of different application scenes can be realized.
Drawings
FIG. 1 is a schematic view of the deployment of each node of a server in embodiment 1;
fig. 2 is a schematic diagram of the overall architecture in embodiment 1.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are 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 present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
As described in fig. 1-2, the present embodiment provides a distributed storage system based on server role and type partitioning. In the distributed storage system, each server has two configurations of type and role. Each server has at least one role, and components not illustrated can run on all nodes, not limited by roles, but limited by server type. The gateway server may set a block storage gateway role, an object storage gateway role, and a file storage gateway role, and typically the gateway service and the storage service may be co-deployed on one server.
1. Server type
(1) Gateway server
Gateway servers refer to nodes that provide librbd functionality when interfaced with a front-end application node (e.g., a computing node of OpenStack or Stack). The gateway node installs less software and fewer services are initiated.
(2) Storage server
The storage server may run mon, mgr, osd, etc. services, may install a hard disk, and run Pool components to manage storage space on the hard disk.
2. Server roles
The server role configuration is five, and the components corresponding to each role are as follows:
(1) Management roles: and the management function of the whole cluster is responsible, the control end of the controller is operated, and the non-management role is operated by the agent end.
(2) Monitoring roles: and running the mon service, maintaining the whole cluster state and collecting, updating and publishing cluster information.
(3) Block storage gateway role: the Block component is run, providing a SCSI-based protocol interface.
(4) Object storage gateway roles: the Object component is run, providing an access interface based on the S3 protocol.
(5) File storage gateway role: and operating the File component to build a File system for the cluster.
In this embodiment, a unified distributed storage cluster is deployed by using a plurality of rack-mounted servers, as shown in fig. 1, and in order to implement multi-protocol support of the cluster, the cluster is respectively deployed with a management node, a monitoring node, a block storage gateway node, a file storage gateway node, and an object storage gateway node.
In the cluster, a block storage pool, a file storage pool and an object storage pool are respectively divided for different types of services, and the storage pools respectively provide block, file and object storage services to the outside through corresponding gateway nodes. As shown in fig. 2, the block storage gateway is responsible for receiving and processing the block storage request, the file storage gateway is responsible for receiving and processing the file storage request, the object storage gateway is responsible for receiving and processing the object storage request, the management node is responsible for overall management of the cluster, and the monitoring node is responsible for maintaining the state of the whole cluster, such as updating the cluster map.
The client acquires the Map copy of the cluster from mon by calling the block, file and object gateway service to obtain the state and configuration information of the cluster, and the block, file and object IO requests are determined to correspond to the OSD positions of the block, file and object storage pool after a series of algorithms, and corresponding read-write operations are executed.
The clusters are deployed in a distributed architecture by using servers, are managed in a unified mode, deploy a plurality of roles of a block storage gateway, a file storage gateway, an object storage gateway, manage and monitor, and according to planning, block, file and object gateway services are deployed in different servers, and redundancy is ensured by the management roles and the monitoring roles. The block, file and object storage application are respectively in butt joint through the block, file and object gateway, so that multi-protocol support of the cluster is realized. Different storage pools are respectively configured for block, file and object scenes, so that isolation of data traffic among protocols is not needed.
Compared with the traditional storage deployment scheme, the embodiment is based on the rack-mounted server, adopts a distributed architecture, supports RBD, NFS, CIFS, S and other multi-storage protocols, can meet the requirements of different application scenes, and can realize the isolation of data traffic of different application scenes. The distributed architecture is adopted, so that the deployment is flexible and easy to expand; the multi-cabinet deployment optimizes the fault domain design, and the system is safer and more reliable; the cluster is managed in a unified way, the server is configured in multiple roles, a plurality of protocols such as rbd, nfs, cifs, s3 are supported, and one cluster can respectively provide block, file and object storage according to front-end service requirements.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A distributed storage system based on server role and type partitioning, comprising:
the storage servers are used for managing storage space, mon, mgr and osd services are operated on the storage servers, and the storage servers are divided into a plurality of storage pools in advance;
a plurality of gateway servers for providing librbd functionality and enabling data interaction when interfacing with the front-end application node, the plurality of gateway servers being matched with the plurality of storage pools,
the plurality of storage servers and the plurality of gateway servers form a server cluster, and at least one of the following roles is provided for any server in the server cluster:
a management role, wherein a server with the management role is used for managing the server cluster;
the monitoring role, the server with the monitoring role is used for maintaining the state of the server cluster through collecting, updating and releasing cluster information;
a block storage gateway role, a server having the block storage gateway role for providing a SCSI-based protocol interface;
an object storage gateway role, the server having the object storage gateway role for providing an S3 protocol based access interface;
and the server with the file storage gateway role is used for providing file service for the server cluster.
2. A distributed storage system based on server role and type partitioning according to claim 1, wherein at least one hard disk is provided on each of said storage servers.
3. The server role and type partitioning based distributed storage system of claim 1, wherein said plurality of gateway servers interface one-to-one with said plurality of storage pools.
4. The server role and type partitioning based distributed storage system of claim 1, wherein said plurality of storage pools comprises a block storage pool, a file storage pool, and a gateway storage pool.
5. The distributed storage system based on server role and type division according to claim 1, wherein after an external request is received, a Map copy of the server cluster is obtained through a server with the monitoring role, and determination of a target storage server is achieved according to the Map copy, so that data interaction is achieved.
6. The distributed storage system based on server role and type partitioning according to claim 1, wherein said plurality of storage servers implement storage space management by running Pool components.
7. A distributed storage system based on server role and type partitioning as in claim 1, wherein a mon service is running on a server having said monitor role.
8. The distributed storage system based on server role and type partitioning as set forth in claim 1, wherein a Block component is running on a server having said Block storage gateway role.
9. The server role and type partitioning based distributed storage system of claim 1, wherein servers with the Object storage gateway role run with Object components.
10. A distributed storage system based on server roles and type partitioning as recited in claim 1, wherein a File component runs on a server having the File storage gateway role.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211697223.9A CN116132460A (en) | 2022-12-28 | 2022-12-28 | Distributed storage system based on server role and type division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211697223.9A CN116132460A (en) | 2022-12-28 | 2022-12-28 | Distributed storage system based on server role and type division |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116132460A true CN116132460A (en) | 2023-05-16 |
Family
ID=86294936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211697223.9A Pending CN116132460A (en) | 2022-12-28 | 2022-12-28 | Distributed storage system based on server role and type division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116132460A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118213045A (en) * | 2024-02-07 | 2024-06-18 | 深圳市慧医合创科技有限公司 | Image data storage method, system, medium and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111698311A (en) * | 2020-06-08 | 2020-09-22 | 星辰天合（北京）数据科技有限公司 | Node control method and device of distributed storage cluster and electronic equipment |
| CN111813332A (en) * | 2020-05-21 | 2020-10-23 | 华北电力大学 | An intelligent distributed storage system with high performance, high expansion and high security |
| CN112433678A (en) * | 2020-11-26 | 2021-03-02 | 湖南国科微电子股份有限公司 | Network adjusting method, device, equipment and medium for distributed storage system |
| US20220374321A1 (en) * | 2021-04-23 | 2022-11-24 | Netapp, Inc. | Methods and systems for a non-disruptive planned failover from a primary copy of data at a primary storage system to a mirror copy of the data at a cross-site secondary storage system without using an external mediator |
-
2022
- 2022-12-28 CN CN202211697223.9A patent/CN116132460A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111813332A (en) * | 2020-05-21 | 2020-10-23 | 华北电力大学 | An intelligent distributed storage system with high performance, high expansion and high security |
| CN111698311A (en) * | 2020-06-08 | 2020-09-22 | 星辰天合（北京）数据科技有限公司 | Node control method and device of distributed storage cluster and electronic equipment |
| CN112433678A (en) * | 2020-11-26 | 2021-03-02 | 湖南国科微电子股份有限公司 | Network adjusting method, device, equipment and medium for distributed storage system |
| US20220374321A1 (en) * | 2021-04-23 | 2022-11-24 | Netapp, Inc. | Methods and systems for a non-disruptive planned failover from a primary copy of data at a primary storage system to a mirror copy of the data at a cross-site secondary storage system without using an external mediator |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118213045A (en) * | 2024-02-07 | 2024-06-18 | 深圳市慧医合创科技有限公司 | Image data storage method, system, medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6056453B2 (en) | Program, data management method, and information processing apparatus | |
| US8145873B2 (en) | Data management method for network storage system and the network storage system built thereof | |
| EP1991936B1 (en) | Network topology for a scalable data storage system | |
| CN102652423A (en) | Cluster families for cluster selection and cooperative replication | |
| US20070061379A1 (en) | Method and apparatus for sequencing transactions globally in a distributed database cluster | |
| US7941455B2 (en) | Notification for a distributed file system | |
| CN110912991A (en) | Super-fusion-based high-availability implementation method for double nodes | |
| US20090049054A1 (en) | Method and apparatus for sequencing transactions globally in distributed database cluster | |
| US20070226224A1 (en) | Data storage system | |
| US9589002B2 (en) | Content selection for storage tiering | |
| CN112887367B (en) | Method, system and computer readable medium for realizing high availability of distributed cluster | |
| CN105897859B (en) | Storage system | |
| WO2020118955A1 (en) | Distributed metadata management consistency ensuring method, device and system, and application | |
| CN112416892A (en) | Emergency video data cloud storage system | |
| US20110296422A1 (en) | Switch-Aware Parallel File System | |
| CN101808127A (en) | Data backup method, system and server | |
| CN102117287A (en) | Distributed file system access method, a metadata server and client side | |
| US7734591B1 (en) | Coherent device to device data replication | |
| CN103384266A (en) | Parastor200 management node high availability method based on real-time synchronization at file level | |
| CN109639773A (en) | A kind of the distributed data cluster control system and its method of dynamic construction | |
| CN114077517A (en) | Data processing method, device and system | |
| CN104598568A (en) | High-efficiency and low-power-consumption offline storage system and method | |
| CN116132460A (en) | Distributed storage system based on server role and type division | |
| US9342418B2 (en) | Storage system, storage control device and data transfer method | |
| WO2020135889A1 (en) | Method for dynamic loading of disk and cloud storage system |
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 |