A method of making an MFS distributed file system highly available
A distributed file, high-availability technology, which is applied to the generation of response errors, special data processing applications, and redundant data error detection in operations. It can solve problems such as system unavailability, and improve robustness, high performance Availability of services, effect of strong rollback capability
Inactive Publication Date: 2018-12-25
GEOVIS CO LTD
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in this scheme, a large amount of data needs to be synchronized when the master and slave nodes are initialized, which results in a long system initialization process. During this period, once the master node has a problem, the system enters an unavailable state
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0017] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0018] Such as figure 1 A method for making the MFS distributed file system highly available is shown. The MFS distributed file system used in this method adds a mirror master node (second master) and a metadata on top of the original MFS original roles and modules. Synchronization module; the mirror master node is responsible for keeping the state consistent with the master node (master); the metadata synchronization module is located between the master node and the mirror master node, and is responsible for the synchronization of metadata benchmark data and metadata incremental modification log (changelog). Authorization verification of nodes and mirror master nodes, etc.; MFS is a fault-tolerant network distributed file system, which stores data scattered on multiple physical servers, and presents a unified resource to users.
[0...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for making the MFS distributed file system have high availability. The MFS distributed file system used in the method adds a mirror main node and a metadata synchronization module on the original MFS original role and module; the MFS distributed file system comprises a mirror main node and a metadata synchronization module. The mirror master node is responsible forkeeping the state consistent with the master node. The metadata synchronization module is located between the master node and the mirror master node, which is responsible for synchronizing the metadata base data and the metadata incremental modification log, and verifying the authorization of the master node and the mirror master node. The invention transmits the reference metadata of the masternode and the incremental modification log by the master-slave synchronization mechanism to maintain the weak consistency of the metadata of the master node and the mirror node. When the primary node stops serving, the mirror node can quickly promote the primary node and provide storage services to ensure that the primary node is highly available, and at the same time, the operation can be rolled back, thus ensuring the high availability of the MFS file system services.
Description
technical field [0001] The invention relates to an improved method, in particular to a method for making the MFS distributed file system highly available. Background technique [0002] The MFS distributed file system borrows from Google's GFS file system design ideas and adopts a master-slave architecture design. The meta information of the file system is stored on the master node (master), and the client obtains the specific location of the data by communicating with the master node, and then initiates a data read request for the specific data location. This method of separating file meta information from data information and the master-slave architecture can bring better system scalability and simpler data management. However, since all meta information is stored on the master node, once the master node appears problem, the entire file system will fail. [0003] In the current practice of various systems, the master-slave synchronization mechanism is generally adopted to...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F17/30G06F11/14
CPCG06F11/1464
Inventor 吴方才孙兆国孙思远张丽
Owner GEOVIS CO LTD