Cluster storage system and data storage method thereof
A cluster storage and shared storage technology, applied in transmission systems, electrical components, etc., can solve problems such as low disk utilization, capacity limitations, business system suspension, etc., to facilitate data management and improve disaster tolerance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] Based on the above idea, this embodiment provides a cluster storage system, the system architecture is as follows figure 1 As shown, it includes a bit data classification server, a distributed replicated block device (DRBD, Distributed Replicated Block Device) and a shared storage device. In this embodiment, the shared storage device uses a shared array, and the shared array is used to meet the needs of business-level HA to ensure that nodes appear. The service will not be interrupted in the event of a failure, and DRBD is used to meet the requirements of storage-level HA to ensure that important data will not be lost. From figure 1 It can be seen that all nodes are connected to the shared array, and the two meta-nodes are also installed with DRBD in addition to being connected to the shared array.
[0030] Among them, the data classification server is located on the two meta nodes, and it is mainly responsible for constructing a data extraction model for the files in ...
Embodiment 2
[0045]Based on the above-mentioned cluster storage system, this embodiment proposes a data storage method for a cluster storage system, the core of which is to screen data, and place important data (that is, the data of files whose priority value is greater than the set value) in the distributed replication block In the device (DRBD, Distributed Replicated Block Device), the general data (that is, the data of the file whose priority value is less than the set value) is placed in the shared storage device (be the shared array in this embodiment), so that even if the shared array is damaged, Data loss can also be minimized, and important system information (such as server configuration files, administrator information, log information, etc. are determined by the administrator) will be backed up in DRBD to quickly recover when the cluster crashes.
[0046] Specifically, the method includes: the cluster storage system determines the priority value of each file in the shared storage...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com