Performing file prediction with a program-based successor model

Abstract

Recent increases in CPU performance have surpassed those in hard drives. As a result, disk operations have become more expensive in terms of the number of CPU cycles spent waiting for them to complete. File prediction can mitigate this problem by prefetching files into cache before they are accessed. Identifying relationships between individual files plays a key role in successfully performing file prefetching. It is well-known that previous patterns of file references can be used to predict future references. Nevertheless, knowledge about the programs producing the relationships between individual files has rarely been investigated. We present a Program-Based Successor (PBS) model that identifies relationships between files through the names of the programs accessing them. We develop a Program-based Last Successor (PLS) model derived from PBS to do file prediction. Our simulation results show that PLS makes 21 % fewer incorrect predictions and roughly the same number of correct predictions as the Last-Successor (LS) model. We also examine the cache hit ratio achieved by applying PLS to the Least Recently Used (LRU) caching algorithm and show that a cache using PLS and LRU together can perform better than a cache up to 40 times larger using LRU alone. Finally, we argue that because program-based successors are more likely to be used soon, incorrectly prefetched program-based successors are more likely to be used and thus less incorrect than incorrectly prefetched files from non-program-based models.

An activity-based replica placement method of energy-conservation

“…The other, the model based on recently accessing information typical representatives: LS (Last Successor) model using the latest successor to the current accessing file as the prediction results, based on LS models constructed PLS [19] model, ULS [20] model and PULS [21] model. In these prediction models, the main use of the file attributes include the number of users to access the file, the size of the requested data, the time characteristic, file access times (repeatability) and I/O operation types etc.…”

A performance analysis of a cache-based file prediction protocol for mobile file systems

“…However, if a file is not in the cache, the system works out to fetch this file to cache. T. Yeh and S. Brandt [7,8,9] present a Program-Based Successor (PBS) model, which identifies relationships between individual files through the names of the programs accessing them. They base their design on the assumption that relationships between files are caused by program and programs access almost the same files in roughly the same order every time they execute.…”

“…The problem is not new and is in fact worsening as recent increases in CPU and memory speeds have exceeded those in physical disks [11]. On the other hand, studies [8,9,10] have shown that file access behavior is not random, and therefore, two main techniques can be used to work out the latency problem, namely caching and prefetching. Caching keeps in memory the data that are the most likely to be used again, while prefetching attempts to bring data in memory before they are needed.…”

“…Consequently, incorrect predictions can lower the overall performance of the system regardless of the accuracy of correct prediction. Therefore, the success of file prefetching depends on file prediction accuracy [8].…”

A stochastic approach to file access prediction

“…Finally, Yeh et al [15] investigated a simple but effective successor model that identifies the relationships between files through identification of the programs accessing them.…”