A resource management method and resource management system based on multi-tenant cloud storage

Abstract

The invention discloses a resource management method and system based on multi-tenant cloud storage, and the method comprises the steps: obtaining the tenant performance demands of each tenant, and correspondingly recording the tenant performance demands in metadata of a virtual machine mirror image file used by the tenant; adding a token bucket to the metadata of each virtual machine mirror imagefile; in a page cache layer of the IO stack, obtaining an index node object of the accessed virtual machine mirror image file, and scheduling memory resources by utilizing a token bucket algorithm; converting the file IO request into a corresponding block IO request in a file system layer of an IO stack; for each file IO request, obtaining an index node object of a virtual machine mirror image file accessed by the file IO request, obtaining a tenant performance demand from the index node object, and adding the tenant performance demand to each block IO request obtained by converting the fileIO request; and in a block layer of the IO stack, obtaining tenant performance requirements from the block IO request, and scheduling hard disk resources by utilizing a token bucket algorithm. According to the invention, performance isolation between tenants can be effectively realized.

Description

technical field [0001] The invention belongs to the field of cloud storage, and more specifically relates to a resource management method and management system based on multi-tenant cloud storage. Background technique [0002] More and more enterprises and users deploy loads in the cloud environment by renting virtual machines. In order to simplify management and reduce costs, cloud providers store virtual machines in the form of large files on shared storage servers connected to the network. . However, shared storage will cause resource competition among tenants, which will interfere with each other's performance. [0003] In order to ensure the performance requirements of different tenants and achieve performance isolation between tenants, most of the existing methods implement resource management through IO scheduling at the hypervisor layer, and some methods cooperate with the hypervisor and storage servers to implement resource management. These IO scheduling methods ...

AI Technical Summary

Problems solved by technology

These IO scheduling methods do not take into account the impact of the file system on the storage server side, which makes it impossible to understand the usage of the underlying storage resources. For example, if an IO request sent by a virtual machine reaches the storage server side, if the request is served by the page cache, then it It will not consume hard disk resources. If it is a write request, due to the log mechanism used by the file system, etc., it may cause additional write operations, thus consuming more hard disk resources.

If you don't know the resource usage, you can't allocate resources accurately, so the performance of tenants can't be guaranteed, and performance isolation is ineffective.

Images