Sang-Won Lee

Dr. Sang-Won Lee


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2015 in The VLDB Journal
Verified
Journal Article
Closed access
PDF file
WKWoon-Hak Kang
Woon-Hak Kang
SLSang-Won Lee
Sang-Won Lee
BMBongki Moon
Bongki Moon

1 August 2020 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
MKMinji Kang
Minji Kang
SCSoyee Choi
Soyee Choi
GOGihwan Oh
Gihwan Oh
SLSang-Won Lee
Sang-Won Lee
Given skewed writes common in databases, the conventional 1R-Greedy FTL incurs huge write amplification, most of which is contributed by cold pages amounting to 80% of data. Since 1R-Greedy manages all flash blocks in one region at no type distinction, cold pages will be mixed with non-cold ones in the same blocks, spread across blocks over time, and thus repeatedly relocated upon garbage collections. In this paper, we propose "two region" FTL (2R in short); with two flash regions of normal and cold, it focuses on isolating cold pages into cold region and thus preventing their repetitive relocations. 2R has two versions. The optimized version, 2R-FIFO , can further prevent the problem of false cold pages in the basic version, 2R-Greedy , by taking FIFO instead of Greedy as its victim selection policy. 2R is unique in that all its design decisions, including page placement and migration between regions, cold page identification, victim block selection, and space allocation among regions, capitalize on workload characteristics such as write skews, temporal locality, and frozen pages. Thanks to the principled approach, 2R is, unlike the existing hot/cold separation FTLs, a statistics-free and practical solution which can efficiently and effectively separate cold pages using only two regions. Experimental results using a real OpenSSD as well as trace-driven simulations confirm that 2R-FIFO can, compared to 1R-Greedy , halve the write amplification in two OLTP benchmarks, TPC-C and LinkBench, thereby doubling IO performance and transaction throughput. In particular, as flash storage becomes nearly full, 2R-FIFO starts outperforming 1R-Greedy by 4x or more.

1 May 2021 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
Jong-Hyeok ParkJong-Hyeok Park
Jong-Hyeok Park
SCSoyee Choi
Soyee Choi
GOGihwan Oh
Gihwan Oh
SLSang-Won Lee
Sang-Won Lee
Every database engine runs on top of an operating system in the host, strictly separated with the storage. This more-than-half-century-old IHDE (In-Host-Database-Engine) architecture, however, reveals its limitations when run on fast flash memory SSDs. In particular, the IO stacks incur significant run-time overhead and also hinder vertical optimizations between database engines and SSDs. In this paper, we envisage a new database architecture, called SaS (SSD as SQL database engine), where a full-blown SQL database engine runs inside SSD, tightly integrated with SSD architecture without intervening kernel stacks. As IO stacks are removed, SaS is free from their run-time overhead and further can explore numerous vertical optimizations between database engine and SSD. SaS evolves SSD from dummy block device to database server with SQL as its primary interface. The benefit of SaS will be more outstanding in the data centers where the distance between database engine and the storage is ever widening because of virtualization, storage disaggregation, and open software stacks. The advent of computational SSDs with more compute resource will enable SaS to be more viable and attractive database architecture.

31 October 2006 in Journal of Systems Architecture
Verified
Journal Article
Closed access
SLSang-Won Lee
Sang-Won Lee
JAJung-Ho Ahn
Jung-Ho Ahn
HKHyoung-Joo Kim
Hyoung-Joo Kim

1 February 2021 in Electronics
Verified
Journal Article
Open access
PDF file
JPJonghyeok Park
Jonghyeok Park
DPDong-Joo Park
Dong-Joo Park
Tae-Sun ChungTae-Sun Chung
Tae-Sun Chung
SLSang-Won Lee
Sang-Won Lee
An FTL (flash translation layer), which most flash storage devices are equipped with, needs to guarantee the consistency of modified metadata from a sudden power failure. This crash recovery scheme significantly affects the writing performance of a flash storage device during its normal operation, as well as its reliability and recovery performance; therefore, it is desirable to make the crash recovery scheme efficient. Despite the practical importance of a crash recovery scheme in an FTL, few works exist that deal with the crash recovery issue in FTL in a comprehensive manner. This study proposed a novel crash recovery scheme called FastCheck for a hybrid mapping FTL called Fully Associative Sector Translation (FAST). FastCheck can efficiently secure the newly generated address-mapping information using periodic checkpoints, and at the same time, leverages the characteristics of an FAST FTL, where the log blocks in a log area are used in a round-robin way. Thus, it provides two major advantages over the existing FTL recovery schemes: one is having a low logging overhead during normal operations in the FTL and the other to have a fast recovery time in an environment where the log provisioning rate is relatively high, e.g., over 20%, and the flash memory capacity is very large, e.g., 32 GB or 64 GB.

12 April 2021 in IEEE Access
Verified
Journal Article
Open access
JLJongbaeg Lee
Jongbaeg Lee
GOGihwan Oh
Gihwan Oh
SLSang-Won Lee
Sang-Won Lee
Append-only B-tree based key-value stores provide superior search and update performance based on their structural characteristics; however, they periodically require the compaction task that incurs significant I/O overhead. In this paper, we present that the compaction's degraded read performance deteriorates the overall performance in ForestDB, a representative append-only B-tree engine. We demonstrate that despite the exceptional performance of the SSD, the cause of the slow read performance is the underutilization of the SSD's internal parallelism due to the read operations using synchronous I/O. Furthermore, this paper proposes a novel compaction method that improves the compaction's read performance by exploiting SSD's internal parallelism by requesting multiple read operations in a batch using the asynchronous I/O technique. We implemented our proposed methods on ForestDB using two Linux asynchronous I/O interfaces, AIO and io_uring. The evaluation results confirm that our method drastically improves the compaction's read performance up to ten times compared to the conventional compaction method. In particular, we confirmed that the proposed method using io_uring, the latest asynchronous I/O interface, is effective regardless of the file I/O mode and outperforms the others in all cases.