Data management method, equipment and system

Abstract

The embodiment of the invention provides a data management method, equipment and system. Data partitioning of cold data fragments in a first storage equipment is obtained; special data partitioning is found in or separated from the data partitioning where the cold data fragments are located, and data fragments included in the special data partitioning are all the cold data fragments; the special data partitioning is transferred from the first storage equipment to a second storage equipment, and the data processing capability of the first storage equipment is stronger than that of the second storage equipment; the special data partitioning is set as an offline mode, so that the cold data fragments in the special data partitioning can not be accessed. According to the data management method, equipment and system, an external storage medium, manual transference for cold data fragments and complicated operation processes are not needed through setting the partitioning of the cold data fragments as the offline mode, the purpose that when hot data is accessed as planned, the cold data fragments can not be accessed by accident is achieved, and the resulting problems that the response time for query is prolonged and the query capability is decreased are avoided.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a data management method, device and system. Background technique [0002] With the popularity of mobile terminals, cloud computing and the Internet of Things, and the follow-up of industry regulatory requirements, we are entering an era of rapid data expansion. How to design a more cost-effective storage and access strategy for a large amount of inflated data is a hot research topic in the field of storage and data. According to the degree of hotness and coldness of the data, it can be simply divided into hot data and cold data. In fact, frequently accessed hot data tends to account for a relatively small proportion, generally 10%-15%, and most of the remaining data is cold data. For these cold data, there is not much demand for computing power, and generally it only needs to be well stored and managed. In reality, data models that are generated in chronologica...

AI Technical Summary

Problems solved by technology

The query range is wrong and cold data is accidentally accessed, the query speed will slow down or the query result will be wrong. If the user finds out, he can withdraw and re-enter the search midway, but this has already wasted time, and realizes that the probability of problems in his search is not very high. The user withdraws and re-enters the operation midway, and it may reach the level of ten seconds or even tens of seconds from input to response

[0014] In the existing technology, on the premise of ensuring the reduction of cold data overhead, in order to prevent accidental access to cold data when querying hot data, the cold data can be removed from the local cold data storage device through regular manual operations and backed up to an external cold data storage device , however, backups and future re-reading require reconnection to external cold data storage devices, and data needs to be moved and moved regularly. The entire operation process is complicated, and the read and write operations consume a long time

Images