Cloud storage resource distribution method and system

Abstract

The invention relates to the field of cloud storage and discloses a cloud storage resource distribution method and system. The cloud storage resource distribution method includes the steps that when a request, for locking shared resources, of a client side is received, a lock node of the shared resources and a client side lock identity node are created in a synchronous storage space; if the lock node does not exist in the synchronous storage space, the lock node is created successfully, and the client side exclusively uses the shared resources; if the lock node exists in the synchronous storage space already, the lock node is not created successfully, an own client side identity node is created, and other client side lock identity nodes which are created lately are registered and observed; when the shared resources are unlocked, corresponding lock node and the client side lock identity node are deleted, and the client side which registers and observes the client side lock identity node is notified. Dead halt of distributed service nodes cannot lead to deadlock, the problem of single-point fault is solved, high reliability is realized, the client side which registers and observes is notified timely when lock resources are released, each client side does not need to poll lock state, system expenditure is saved, and distribution efficiency of the lock resources is improved.

Description

technical field [0001] The invention relates to the field of cloud storage, in particular to a cloud storage resource allocation method and system thereof. Background technique [0002] Inter-process locking in a stand-alone system can use semaphores or condition variables, and the operation is very easy. However, in a cluster system, common locking methods are difficult to apply to the protection of shared resources when multiple clients access concurrently to shared resources. [0003] The video cloud storage system adopts cluster technology to solve single point of failure. Each server node equally distributes client service requests through load scheduling, and shares database resources through data processing modules. Among them, cluster management (selection of the master node / delivery of management node operation commands), protection of shared database resources, etc. must be protected by distributed lock technology, otherwise unexpected results will be brought. ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a cloud storage resource allocation method and its system, which will not cause deadlock when a distributed service node crashes, and the application and release of locks does not depend on any service node, which solves the single point of failure problem. The system has high reliability. Through the registration observation mechanism, the registered observation client is notified in time when the lock resource is released. Each client does not need to poll the lock status, which saves system overhead and improves the allocation efficiency of lock resources.

Images