<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <title>Repository Collection: null</title>
  <link rel="alternate" href="https://scholar.dgist.ac.kr/handle/20.500.11750/6300" />
  <subtitle />
  <id>https://scholar.dgist.ac.kr/handle/20.500.11750/6300</id>
  <updated>2026-04-04T14:58:22Z</updated>
  <dc:date>2026-04-04T14:58:22Z</dc:date>
  <entry>
    <title>Revisiting Trim for CXL Memory</title>
    <link rel="alternate" href="https://scholar.dgist.ac.kr/handle/20.500.11750/60060" />
    <author>
      <name>Lee, Hayan</name>
    </author>
    <author>
      <name>Kim, Jungwoo</name>
    </author>
    <author>
      <name>Lee, Wookyung</name>
    </author>
    <author>
      <name>Park, Juhyung</name>
    </author>
    <author>
      <name>Jung, Sanghyuk</name>
    </author>
    <author>
      <name>Han, Jinki</name>
    </author>
    <author>
      <name>Kim, Bryan S.</name>
    </author>
    <author>
      <name>Lee, Sungjin</name>
    </author>
    <author>
      <name>Lee, Eunji</name>
    </author>
    <id>https://scholar.dgist.ac.kr/handle/20.500.11750/60060</id>
    <updated>2026-02-10T14:10:18Z</updated>
    <published>2025-07-09T15:00:00Z</published>
    <summary type="text">Title: Revisiting Trim for CXL Memory
Author(s): Lee, Hayan; Kim, Jungwoo; Lee, Wookyung; Park, Juhyung; Jung, Sanghyuk; Han, Jinki; Kim, Bryan S.; Lee, Sungjin; Lee, Eunji
Abstract: The expansion of memory disaggregation, driven by datacentric applications, increases heterogeneity in memory systems. This shift enables the use of inexpensive, yet lifetimelimited, flash memory to be used as a memory expansion module. We argue that TRIM should be introduced into memory management systems to effectively respond to this transition. In this position paper, we explore the potential adoption of flash memory as memory expansion and present an analytical model that offers a straightforward yet rigorous evaluation of TRIM&amp;apos;s effectiveness. Using this model and characteristics extracted from real-world workloads, we evaluate the effectiveness of TRIM in scalable memory systems and prove its necessity.</summary>
    <dc:date>2025-07-09T15:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Lightweight KV-based Distributed Store for Datacenters</title>
    <link rel="alternate" href="https://scholar.dgist.ac.kr/handle/20.500.11750/58953" />
    <author>
      <name>Chung, Chanwoo</name>
    </author>
    <author>
      <name>Koo, Jinhyung</name>
    </author>
    <author>
      <name>Arvind</name>
    </author>
    <author>
      <name>Lee, Sungjin</name>
    </author>
    <id>https://scholar.dgist.ac.kr/handle/20.500.11750/58953</id>
    <updated>2025-08-26T09:10:10Z</updated>
    <published>2017-07-09T15:00:00Z</published>
    <summary type="text">Title: Lightweight KV-based Distributed Store for Datacenters
Author(s): Chung, Chanwoo; Koo, Jinhyung; Arvind; Lee, Sungjin
Abstract: A great deal of digital data is generated every day by content providers, end-users, and even IoT sensors. This data is stored in and managed by thousands of distributed storage nodes, each comprised of a power-hungry x86 Xeon server with a huge amount of DRAM and an array of HDDs or SSDs grouped by RAID. Such clusters take up a large amount of space in datacenters and require a lot of electricity and cooling facilities. Therefore, packing as much data as possible into a smaller datacenter space and managing it in an energy- and performance-efficient manner can result in enormous savings.</summary>
    <dc:date>2017-07-09T15:00:00Z</dc:date>
  </entry>
  <entry>
    <title>ScaleCache: A Scalable Page Cache for Multiple Solid-State Drives</title>
    <link rel="alternate" href="https://scholar.dgist.ac.kr/handle/20.500.11750/57853" />
    <author>
      <name>Pham, Kiet Tuan</name>
    </author>
    <author>
      <name>Cho, Seokjoo</name>
    </author>
    <author>
      <name>Lee, Sangjin</name>
    </author>
    <author>
      <name>Nguyen, Lan Anh</name>
    </author>
    <author>
      <name>Yeo, Hyeongi</name>
    </author>
    <author>
      <name>Jeong, Ipoom</name>
    </author>
    <author>
      <name>Lee, Sungjin</name>
    </author>
    <author>
      <name>Kim, Nam Sung</name>
    </author>
    <author>
      <name>Son, Yongseok</name>
    </author>
    <id>https://scholar.dgist.ac.kr/handle/20.500.11750/57853</id>
    <updated>2025-07-25T02:45:29Z</updated>
    <published>2024-04-23T15:00:00Z</published>
    <summary type="text">Title: ScaleCache: A Scalable Page Cache for Multiple Solid-State Drives
Author(s): Pham, Kiet Tuan; Cho, Seokjoo; Lee, Sangjin; Nguyen, Lan Anh; Yeo, Hyeongi; Jeong, Ipoom; Lee, Sungjin; Kim, Nam Sung; Son, Yongseok
Abstract: This paper presents a scalable page cache called ScaleCache for improving SSD scalability. Specifically, we first propose a concurrent data structure of page cache based on XArray (ccXArray) to enable access and update the page cache concurrently. Second, we introduce a direct page flush (dflush) which directly flushes pages to storage devices in a parallel and opportunistic manner. We implement ScaleCache with two techniques in the Linux kernel and evaluate it on a 64-core machine with eight NVMe SSDs. Our evaluations show that ScaleCache improves the performance of Linux file systems by up to 6.81× and 4.50× compared with the existing scheme and scalable scheme for multiple SSDs, respectively.  © 2024 ACM.</summary>
    <dc:date>2024-04-23T15:00:00Z</dc:date>
  </entry>
  <entry>
    <title>플래시 스토리지에서 P/E cycle에 따른 I/O 실행 시간 변화를 고려한 실시간성 보장 수명 연장 기법</title>
    <link rel="alternate" href="https://scholar.dgist.ac.kr/handle/20.500.11750/57778" />
    <author>
      <name>김경택</name>
    </author>
    <author>
      <name>김명석</name>
    </author>
    <author>
      <name>이성진</name>
    </author>
    <author>
      <name>좌훈승</name>
    </author>
    <id>https://scholar.dgist.ac.kr/handle/20.500.11750/57778</id>
    <updated>2025-07-25T03:35:46Z</updated>
    <published>2023-12-19T15:00:00Z</published>
    <summary type="text">Title: 플래시 스토리지에서 P/E cycle에 따른 I/O 실행 시간 변화를 고려한 실시간성 보장 수명 연장 기법
Author(s): 김경택; 김명석; 이성진; 좌훈승
Abstract: 최근의 안전 필수 실시간 시스템들은 기계 학습 및 신경망 기반의 프로그램을 도입함에 따라 정해진 마감 시간 내에 데이터 I/O를 반드시 처리할 수 있어야 한다. 낸드 플래시 기반 스토리지는 빠른 접근 시간 및 비휘발성 특성으로 인해 실시간 시스템에서 사용 가능한 저장장치로써 각광받고 있다. 그러나 낸드 플래시의 경우 플래시 페이지 및 블록의 program-erase cycle 이 증가함에 따라 I/O 실행 시간이 달라지고, 이는 I/O 응답 시간의 변화 및 최악의 경우 마감 시간 초과를 야기한다는 문제가 있다. 본 연 구에서는 그러한 특성을 고려하여 실시간성 보장 여부를 판단하는 schedulability 분석을 정의하고, 이를 기반으로 실시간성 보장 기간을 최대화하는 데이터 관리 기법을 제안한다. 제안하는 관리 기법을 상용 플래시의 일반 기법 및 대표적인 플래시 수명 연장 기법인 wear-leveling 과 비교하였다. 그 결과 일반 기법 대비 최대 78%, wear-leveling 기법 대비 최대 54% 의 실시간성 보장 기간 증가를 확인하였다.</summary>
    <dc:date>2023-12-19T15:00:00Z</dc:date>
  </entry>
</feed>

