Client lock splitting method based on distributed file system

Abstract

The invention discloses a client lock splitting method based on a distributed file system. The method comprises the steps that resource classification is performed according to an inode number of a file, and metadata caches and additional resources are placed in different resource pools; when request processing operation is performed, the resource pool used in the request processing operation is found according to a module value of the inode number of the file, and the resource pool is locked; and the request processing operation is executed, and the lock of the resource pool is released afterthe operation is completed. Through the method, request response delay is shortened on the basis of improving client IOPS.

Description

technical field [0001] The invention relates to the technical field of distributed file systems, in particular to a method for splitting client locks based on distributed file systems. Background technique [0002] At present, for a distributed file system with a cache on the client side, the client is responsible for receiving user requests, forwarding the requests to the metadata server, and performing changes to metadata related to the data cache, and the client performs such operations It will lock the client and prohibit the concurrent processing of the client. That is to say, the client performs request processing and forwarding, and the metadata cache cannot be processed concurrently, which will affect the concurrent capability of the client and the IOPS capability of the distributed file system. For a file system without client cache, the client will process different files concurrently, but the client has no cache, so the request cannot find the metadata information...

AI Technical Summary

Problems solved by technology

[0002] At present, for a distributed file system with a cache on the client side, the client is responsible for receiving user requests, forwarding the requests to the metadata server, and performing changes to metadata related to the data cache, and the client performs such operations It will lock the client and prohibit the concurrent processing of the client. That is to say, the client performs request processing and forwarding. When the metadata cache is changed, it cannot be processed concurrently, which will affect the concurrency capability of the client and further affect the IOPS capability of the distributed file system.

For a file system without client cache, the client will process different files concurrently, but the client has no cache, so the request cannot find the metadata information of the response immediately. After receiving the client request, it will first go to the metadata server to get it Metadata information, and then perform related operations, which will affect the processing and response capabilities of the client

Images