Method, device and system for virtual disk mapping

Abstract

The invention discloses a virtual disk mapping method. The method comprises the steps of acquiring a feature vector of a virtual disk to be mapped and a feature matrix of each data storing device, calculating out a first value vector and a second value vector of each data storing device through a first calculating strategy and a second calculating strategy according to the feature vector of the virtual disk to be mapped and the feature vector of each data storing device, deciding the fit degree between the virtual disk to be mapped and each data storing device according to the first value vector and the second value vector and mapping the virtual disk to be mapped to the data storing device with the highest fit degree with the virtual disk to be mapped. The virtual disk mapping method in the embodiment can directly map the virtual disk to be mapped to the data storing device with the highest fit degree with the virtual disk to be mapped according to the fit degree. Thus, the mapping speed of the virtual disk to be mapped is improved.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a method, device and system for virtual disk mapping. Background technique [0002] In a virtualized storage environment, the hardware layer usually includes multiple data storage devices, and multiple virtual disks in the virtual machine correspond to the data storage devices, that is to say, there is a corresponding relationship between each virtual disk and the data storage device. [0003] Storage Dynamic Resource Scheduler (SDRS, Storage Dynamic Resource Scheduler) is a technology for dynamically adjusting virtual disk placement in a virtual machine environment through means such as storage live migration. [0004] SDRS provides an abstraction layer consisting of a series of data storage devices (DataStore) to shield the underlying operation details and present a unified view of storage resources to users. SDRS mainly includes the following two functions: [0005] (1) In...

AI Technical Summary

Problems solved by technology

However, this method is difficult to meet the rapid increase in the number of data storage and the complex and time-varying trends of application types faced by virtualized cloud data storage systems in the era of big data.

[0008] At present, administrators manually set the adaptability of virtual disks and data storage devices. When the number of managed virtual disks and data storages increases, it will become a very complicated task with a huge workload, which will directly offset the impact of SDRS. The benefits brought by the automation of the management of the entire storage system have become an important bottleneck restricting the effective application of SDRS to large-scale storage systems

Images