ClusterFetch: A lightweight prefetcher for general workloads
- Authors
- Jeong, Haksu; Ryu, Junhee; Lee, Dongeun; Lee, Jaemyoun; Shin, Heonshik; Kang, Kyungtae
- Issue Date
- Jan-2015
- Publisher
- Association for Computing Machinery, Inc
- Keywords
- ClusterFetch; Launch and loading times reduction; Lightweight prefetch
- Citation
- ICPE 2015 - Proceedings of the 6th ACM/SPEC International Conference on Performance Engineering, pp.99 - 100
- Indexed
- OTHER
- Journal Title
- ICPE 2015 - Proceedings of the 6th ACM/SPEC International Conference on Performance Engineering
- Start Page
- 99
- End Page
- 100
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/20556
- DOI
- 10.1145/2668930.2688062
- Abstract
- Application loading times can be reduced by prefetching disk blocks into the buffer cache. Existing prefetching schemes for general workloads suffer from significant overheads and low accuracy. ClusterFetch is a lightweight prefetcher that identifies continuous sequences of I/O requests and identifies the files that trigger them. The next time that the same files are opened, the corresponding disk blocks are prefetched. In experiments, ClusterFetch reduced the launch time, by which we refer to the latency that occurs when a programfirst runs, by 15.2 to 30.9%, and loading times, meaning the delays that are incurred while additional data is loaded from the disk during program execution, by 15.9%. Copyright © 2015 ACM.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > DEPARTMENT OF ARTIFICIAL INTELLIGENCE > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/20556)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.