Cache reading, reading processing method and device

Abstract

A cache reading method and apparatus, and a cache reading processing method and apparatus. The reading method comprises: sending a reading request for multiple data blocks in a local file system (S102); and when it is determined that the multiple data blocks are located in a cache of the local file system and the size of the part, which has been read, of specified data blocks among the multiple data blocks exceeds a preset proportion of the size of the specified data blocks, reading a next data block among the multiple data blocks (S104). By using the technical scheme, the problem in the related art is solved that memory resources cannot be properly used because data blocks are accessed in a form of a sequential access flow; accordingly, a process of asynchronously acquiring multiple data blocks is realized, thereby rapidly increasing the speed of acquiring the data blocks and properly using the memory resources.

Description

technical field [0001] The present invention relates to the communication field, in particular, to a cache reading and reading processing method and device. Background technique [0002] With the development of technologies such as computing, storage, and communication, large-scale streaming media services have been widely used in various fields such as entertainment, education, and commerce. How to realize efficient storage of large-scale streaming media files while supporting high concurrent users is a problem. very critical question. The local file user state caching method in the distributed streaming media service proposed by this patent can not only improve the storage efficiency of streaming media files, but also can be well applied in the distributed storage system based on block storage, for example Taobao File System (Taobao File System, referred to as TFS), Distributed File System (Hadoop Distributed File System, referred to as HDFS) and other systems. [0003] ...

AI Technical Summary

Problems solved by technology

The traditional file system has the following problems in block file storage: the cache of the traditional file system is managed by page_cache (page cache), the hot data of the streaming media file is low, the spatial locality is poor, and the data is mostly accessed in order It is easy to have the problem of cache pollution, so that the memory resources cannot be used reasonably, and the prefetch granularity of the general file system is not high.

[0004] In related technologies, no effective solution has been proposed for the problem that memory resources cannot be reasonably utilized due to the fact that data blocks are accessed in the form of sequential access streams.

Images