Microkernel-based extensible file system and file access method

Abstract

The invention discloses a microkernel-based extensible file system. The system comprises a disk service, a system service, a catalog service process and a plurality of file service processes, wherein the disk service is used for reading and writing disks; the system service is used for copying file data between a user process and the file service processes, and helping the disk service to execute a kernel-mode privilege IO instruction; the catalog service process works on a single processing core to manage global metadata, and is provided with block cache for storing file attribute information inode and catalog information dentry, receiving all the file processing requests of the user process, executing catalog traversal, processing a request of operating the metadata in the file processing requests, and routing a request of reading and writing files to the file service processes; the file service processes are used for processing the request of reading and writing files, and are provided with a cache pool for caching data file blocks. The invention furthermore discloses a file access method of the microkernel-based extensible file system. According to the microkernel-based extensible file system and the file access method, most of the lock contention expenditure can be avoided, and the load balance and elastic extension of the file service processes can be realized.

Description

technical field [0001] The invention relates to a file system and a file access method, in particular to a microkernel-based scalable file system and a file access method, belonging to the technical field of data storage access. Background technique [0002] For web servers or large multi-core workstations, file system parallelism is critical. Especially with the widespread application of distributed storage systems in the era of cloud computing, in a multi-core cloud storage system, for the chunk service process on each core, the efficiency of chunk read and write becomes a key factor, because it is usually necessary to Handle reading and writing of a large number of files in a short period of time. [0003] The current traditional file system can work well when the number of cores is small, but due to the lock contention overhead, its performance will be greatly degraded as the number of parallel code streams increases. Its lock competition overhead mainly comes from the...

AI Technical Summary

Problems solved by technology

When reading and writing files in parallel, there is also a huge contention overhead for the shared block cache in the file system

In addition to the global lock, each block cache entry is controlled by a state value (equivalent to a mutex) to avoid blocks being written at the same time, which makes programs with more write operations less scalable

[0006] At the same time, the unbalanced load between multiple file service processes or the mismatch between user requests and the service capabilities of the service process will also cause unreasonable use of computing resources, resulting in a decline in the overall performance of the file system

Images