A quality-of-service-aware cache scheduling method based on feedback and fair queues

Abstract

The present invention provides a quality-of-service-aware cache scheduling method based on feedback and fair queues, using a quality-of-service measurement strategy to index the quality of service of different similar applications, and using start-time fair queues to set different start service times to control different applications Request service sequence, use the feedback-based cache partition management module to divide all logical partitions into two types: providing partitions and receiving partitions, and adjust the cache allocation between the two types of logical partitions, and balance the whole through the cache block allocation management module The performance and guaranteed service quality, and the cache elimination strategy monitoring module monitor the current cache elimination strategy efficiency of each logical partition, and make dynamic adjustments according to the load characteristics of the application, and use the cache compression monitoring module to capture applications with poor locality, that is, existing The application of the cache hit rate long tail phenomenon. The invention can take into account the overall cache efficiency and the service quality guarantee between applications.

Description

technical field [0001] The invention belongs to the field of cache scheduling of computer system structures, and relates to a cache scheduling method based on feedback and fair queue quality of service perception. Background technique [0002] In recent years, traditional caching algorithms mainly focus on how to improve the cache hit rate. The basic method is to cache the cache blocks that are most likely to be accessed according to the principle of storage access locality. The current storage system is becoming more and more integrated. Not only the number of applications is increasing, but also the types of applications are becoming more and more complex. Different applications often have large differences in load characteristics and access rules. For example, email servers have more random access And there are fewer repeated visits, although the website server has more random visits, some hot web pages have more repeated visits, and video servers have more sequential vis...

AI Technical Summary

Problems solved by technology

Therefore, effective quality of service guarantees cannot be provided; on the other hand, because multiple applications access concurrently, an application access sequence may insert access requests from other applications at any time, but the data correlation between different applications is weak, which makes the load reduced overall locality, especially for applications with low data request arrival rates

Images