[연구] 엄영익 교수 연구실, 박종규 박사과정 SOSP 2021 국제학술대회 한국기관 최초 논문 게재
- 소프트웨어융합대학
- 조회수1712
- 2021-10-01
분산컴퓨팅연구실의 박종규 박사과정(지도교수 엄영익)이 ACM Symposium on Operating Systems Principles (SOSP) 2021에 “FragPicker: A New Defragmentation Tool for Modern Storage Devices” (저자: 박종규, 엄영익) 논문을 게재하였다. 본 논문은 기존 파일 시스템 단편화 제거 기법의 고질적인 문제점인 추가적인 쓰기 발생과 높은 소모 시간을 해결하기 위해 최신 스토리지 디바이스의 내부 특성을 고려한 새로운 단편화 제거 기법을 제안하는 논문이다.
ACM SOSP는 격년으로 개최되는 운영체제 분야 최상위 학술대회로, 이번 SOSP 2021은 총 348편의 논문 중 54편(채택율 15.5%)의 논문이 채택되었다. 특히 본 건은 SOSP 학회 54년 역사상 한국 기관 최초의 논문이라는 데에 의미가 있다.
[논문 정보]
FragPicker: A New Defragmentation Tool for Modern Storage Devices
Jonggyu Park and Young Ik Eom
The 28th ACM Symposium on Operating Systems Principles (SOSP 2021)
Abstract:
File fragmentation has been widely studied for several decades because it negatively influences various I/O activities. To eliminate fragmentation, most defragmentation tools migrate the entire content of files into a new area. Unfortunately, such methods inevitably generate a large amount of I/Os in the process of data migration. For this reason, the conventional tools (i) cause defragmentation to be time-consuming, (ii) significantly degrade the performance of co-running applications, and (iii) even curtail the lifetime of modern storage devices. Consequently, the current usage of defragmentation is very limited although it is necessary.
Our extensive experiments discover that, unlike HDDs, the performance degradation of modern storage devices incurred by fragmentation mainly stems from request splitting, where a single I/O request is split into multiple ones. With this insight, we propose a new defragmentation tool, FragPicker, to minimize the amount of I/Os induced by defragmentation, while significantly improving I/O performance. FragPicker analyzes the I/O activities of applications and migrates only those pieces of data that are crucial to the I/O performance, in order to mitigate the aforementioned problems of existing tools. Experimental results demonstrate that FragPicker efficiently reduces the amount of I/Os for defragmentation while achieving a similar level of performance improvement to the conventional defragmentation schemes.