상세 보기
A2FL: Autonomous and Adaptive File Layout in HPC through Real-time Access Pattern Analysis
- Sung, Dong Kyu;
- Son, Yongseok;
- Sim, Alex;
- Wu, Kesheng;
- Byna, Suren;
- 외 4명
WEB OF SCIENCE
1SCOPUS
3초록
Various scientific applications with different I/O characteristics are executed in HPC systems. However, underlying parallel file systems are unaware of these characteristics of applications, and using a single fixed file layout for all applications can degrade the performance of HPC systems. In this paper, we propose A2FL, an autonomous and adaptive file layout adjustment scheme that optimizes parallel file system configurations by analyzing the access pattern of the applications. The key steps of A2FL are as follows: (1) A2FL initially intercepts the I/O operations of the application, recording their access patterns in real-time. (2) The access patterns are then transformed into a graphical representation used for predicting I/O performance and providing adjustment recommendations. (3) A2FL autonomously adjusts the file layout based on the prediction results, delivering an optimal file layout within the parallel file system. Moreover, we propose A2FL-Compound which analyzes an access pattern by dividing it into smaller components to optimize the file layout in a fine-grained manner. Our evaluations demonstrate that A2FL significantly enhances I/O performance, with improvements of up to 65.9× compared to the default file layout. © 2024 IEEE.
키워드
- 제목
- A2FL: Autonomous and Adaptive File Layout in HPC through Real-time Access Pattern Analysis
- 저자
- Sung, Dong Kyu; Son, Yongseok; Sim, Alex; Wu, Kesheng; Byna, Suren; Tang, Houjun; Eom, Hyeonsang; Kim, Changjong; Kim, Sunggon
- 발행일
- 2024
- 유형
- Proceedings Paper
- 저널명
- Proceedings - 2024 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2024
- 페이지
- 506 ~ 518
- 언어
- ENG
- 출판사
- Institute of Electrical and Electronics Engineers Inc.
- 분량
- 13 페이지
- ISSN
- P 1530-2075