HRFP: Highly Relevant Frequent Patterns-Based Prefetching and Caching Algorithms for Distributed File Systems

Round 1

Reviewer 1 Report

In this paper author proposed frequent pattern-based prefetching, caching, and replacement algorithms. they also compared with the existing Support-based frequent block access pattern prefetching and caching algorithm, Hadoop distributed file system with and without caching, and the proposed algorithm with LRU replacement. 

Author's work looks interesting and their results also satisfactory. 

Author Response

Thank you very much for your kind consideration.

Reviewer 2 Report

This article presents a new highly relevant frequency pattern-based (HRFP) algorithm that prefetches content from a distributed file system environment and stores it in client-side caches that are present in the same environment. A new replacement policy and an efficient migration technique are proposed to move patterns from the main memory cache to the solid-state cache based on a new metric, namely pattern relevance. The simulation results show that the proposed high-relevance prefetching algorithm based on templates and caching outperforms other methods.

The choice of the proposed methods is justified. This approach is relevant. The research is of practical importance.

1. UML diagrams or ISO flowcharts are more visual for describing how an algorithm works.

2. The pictures 2 – 5 need to be improved.

Author Response

Thanks very much for reviewing our work, please see the attached file for the response to your comments.

Author Response File: Author Response.docx

Reviewer 3 Report

This paper presents HRFP: Highly Relevant Frequent Patterns-based Prefetching

and Caching Algorithms for Distributed File Systems. Thus, this paper is directly related to the theme of this journal.

Overall, the paper is organized properly; So, so the paper is accepted after the following major changes:

 

1.       Problem is not clear in the introduction section

2.       Contribution of the paper must be given in bullets in the introduction section.

3.       Heading 2 material methods must be renamed with Related work

4.       Comments of Pseudo algorithms are not given properly to understand of reader

5.       Paper contains a few grammar mistakes which will be cooperated in the final version.

6.       Very old  references are used and mostly before 2016 published papers are cited. It’s better to add new references up to 50.

 

7.       add a few references related, which are mentioned below

Laghari, Asif Ali, Hui He, Rashid Ali Laghari, A. I. Khan, and Rahul Yadav. "Cache performance optimization of QoC framework." (2019). 

Author Response

Thank you for providing insightful comments, please see the response to the comments in the file attached.

Author Response File: Author Response.docx