Cold and hot data identification threshold value calculation method, device and system

Abstract

The invention relates to a cold and hot data identification threshold value calculation method, device and system. The method comprises the following steps of transmitting a data block IO (input / output) statistical information query command to each storage node; receiving IO statistical information from each storage node; performing addition operation on IO count field values in the same count ranges in the IO statistical information received from each storage node, generating an IO count statistical value corresponding to each count range, and obtaining a minimum IO count value in the count range corresponding to a minimum IO count statistical value in high IO count statistical values when data blocks corresponding to the high IO count statistical values are filled with hot data storage media as a cold and hot data identification threshold value according to the overall capacity of the hot data storage media, the sizes of the data blocks and the IO count statistical values in each storage node. According to the method, the device and the system, each storage node in a storage system can independently finish the hierarchical data storage of the whole storage system in a coordination way.

Description

technical field [0001] The invention relates to the technical field of data storage, in particular to a method, device and system for calculating a threshold value for hot and cold data identification. Background technique [0002] With the development of storage technology, people have higher and higher requirements on the capacity and performance of storage systems, but storage systems with large capacity and high performance are also expensive. The need to meet the performance and capacity requirements of storage systems at low prices has given rise to tiered storage technology. [0003] Hierarchical data storage technology is the mainstream technology to meet the needs of data lifecycle management. By monitoring business data, data access frequency, IO count and other parameter values ​​can be recorded. According to the monitored IO and other parameter values, it can be determined which layer of the storage system the business data should be stored in. Hot data can be m...

AI Technical Summary

Problems solved by technology

Under the existing technology, the data monitoring function module, the data hot and cold identification function module and the data migration function module are distributed in each storage node of the storage system, but the whole storage system does not have a uniform hot and cold identification standard, so the layered storage function can only It is completed within a single storage node in the storage system, and data migration across storage nodes cannot be performed, which greatly reduces the practicability and availability of the hierarchical storage function of the storage system.

Images