Solid-State Squad

This is a study group studying SSD, FTL, and FEMU in 2024.

Goal

• Study for Flash Translation layer to Maximize the performance of storage system.
  
• Understanding mapping tables, wear leveling, and garbage collection.
  
• FTL Code Analysis.

논문 발표

	Date	논문	발표자	Link
week01	2024-07-03	OT	최건희
week02	2024-07-10	Rosenblum, Mendel, and John K. Ousterhout. "The design and implementation of a log-structured file system." ACM Transactions on Computer Systems (TOCS) 10.1 (1992): 26-52. Link	김나경	LFS
week02	2024-07-10	Park, Chanik, et al. "A reconfigurable FTL (flash translation layer) architecture for NAND flash-based applications." ACM Transactions on Embedded Computing Systems (TECS) 7.4 (2008): 1-23. Link	구선주, 박수지	RFTL
week03	2024-07-17	Gupta, Aayush, Youngjae Kim, and Bhuvan Urgaonkar. "DFTL: a flash translation layer employing demand-based selective caching of page-level address mappings." Acm Sigplan Notices 44.3 (2009): 229-240. Link	김주현, 이용민	DFTL
week03	2024-07-17	Agrawal, Nitin, et al. "Design tradeoffs for SSD performance." 2008 USENIX Annual Technical Conference (USENIX ATC 08). 2008. Link	김민성, 위다연	SSD_Perf
week04	2024-07-24	Kim, Bryan S., Jongmoo Choi, and Sang Lyul Min. "Design tradeoffs for SSD reliability." 17th USENIX Conference on File and Storage Technologies (FAST 19). 2019. Link	신수환	SSD_Reliabilty
week04	2024-07-24	Oh, Seonggyun, et al. "MIDAS: Minimizing Write Amplification in Log-Structured Systems through Adaptive Group Number and Size Configuration." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link	구선주, 박수지	MiDAS
week05	2024-07-31	휴무
week06	2024-08-07	Sun, Jinghan, et al. "Leaftl: A learning-based flash translation layer for solid-state drives." Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. 2023. Link	최연규	LeaFTL
week06	2024-08-07	Wang, Shengzhe, et al. "LearnedFTL: A Learning-Based Page-Level FTL for Reducing Double Reads in Flash-Based SSDs." 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 2024. Link	김민성, 위다연	LearnedFTL
week07	2024-08-14	Jun, Yuhun, et al. "We Ain't Afraid of No File Fragmentation: Causes and Prevention of Its Performance Impact on Modern Flash SSDs." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link	김주현, 이용민	File_Fragmentation
week07	2024-08-14	Niu, Fuping, et al. "FlashGNN: An In-SSD Accelerator for GNN Training." 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 2024. Link	신수환	FlashGNN
week08	2024-08-21	Kim, Shine, et al. "Behemoth: a flash-centric training accelerator for extreme-scale DNNs." 19th USENIX Conference on File and Storage Technologies (FAST 21). 2021. Link	김나경	Behemoth
week09	2024-08-28	Wong, Daniel Lin-Kit, et al. "Baleen:{ML} Admission & Prefetching for Flash Caches." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link	김보승,오여진	Baleen
week10	2024-09-04	Final Presentation	ALL

FTL 분석 및 개발

	Team	Link
1	김나경, 오여진	dynamic segment in leaftl
2	김보승, 김주현	실험발표
2	신수환	실험발표
3	구선주	Improving_DFTL
4	위다연	Indexing_DFTL
5	이용민	LYM_exp_topic
6	김민성	LearnedFTL_CMT_Model_ratio_tradeoff

참여자

• 학부과정 : 박수지, 김민성, 이용민, 구선주, 위다연, 김보승, 오여진
• 석사과정 : 쥬용지에, 신수환, 김나경, 최연규, 김주현
• 박사과정 : 최건희, 이제연, 신호진

For Beginners

1. 개발자를 위한 SSD (Coding for SSD), Kakao Tech 번역, Link
2. Flash 101 and Flash Managment, Western Digital, Link

List of Papers

1. Rosenblum, Mendel, and John K. Ousterhout. "The design and implementation of a log-structured file system." ACM Transactions on Computer Systems (TOCS) 10.1 (1992): 26-52. Link
2. Park, Chanik, et al. "A reconfigurable FTL (flash translation layer) architecture for NAND flash-based applications." ACM Transactions on Embedded Computing Systems (TECS) 7.4 (2008): 1-23. Link
3. Gupta, Aayush, Youngjae Kim, and Bhuvan Urgaonkar. "DFTL: a flash translation layer employing demand-based selective caching of page-level address mappings." Acm Sigplan Notices 44.3 (2009): 229-240. Link
4. Agrawal, Nitin, et al. "Design tradeoffs for SSD performance." 2008 USENIX Annual Technical Conference (USENIX ATC 08). 2008. Link
5. Kim, Bryan S., Jongmoo Choi, and Sang Lyul Min. "Design tradeoffs for SSD reliability." 17th USENIX Conference on File and Storage Technologies (FAST 19). 2019. Link
6. Oh, Seonggyun, et al. "MIDAS: Minimizing Write Amplification in Log-Structured Systems through Adaptive Group Number and Size Configuration." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link
7. Jun, Yuhun, et al. "We Ain't Afraid of No File Fragmentation: Causes and Prevention of Its Performance Impact on Modern Flash SSDs." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link
8. Sun, Jinghan, et al. "Leaftl: A learning-based flash translation layer for solid-state drives." Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. 2023. Link
9. Wang, Shengzhe, et al. "LearnedFTL: A Learning-Based Page-Level FTL for Reducing Double Reads in Flash-Based SSDs." 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 2024. Link
10. Niu, Fuping, et al. "FlashGNN: An In-SSD Accelerator for GNN Training." 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 2024. Link
11. Kim, Shine, et al. "Behemoth: a flash-centric training accelerator for extreme-scale DNNs." 19th USENIX Conference on File and Storage Technologies (FAST 21). 2021. Link
12. Wong, Daniel Lin-Kit, et al. "Baleen: ML Admission & Prefetching for Flash Caches." 22nd USENIX Conference on File and Storage Technologies (FAST 24). 2024. Link

Simulation

1. FEMU, Li, Huaicheng, et al. "The CASE of FEMU: Cheap, accurate, scalable and extensible flash emulator." 16th USENIX Conference on File and Storage Technologies (FAST 18). 2018. Paper Link Git
2. NVMeVirt, Kim, Sang-Hoon, et al. "{NVMeVirt}: A Versatile Software-defined Virtual {NVMe} Device." 21st USENIX Conference on File and Storage Technologies (FAST 23). 2023. Paper Link Git
3. MQSim, Tavakkol, Arash, et al. "{MQSim}: A framework for enabling realistic studies of modern Multi-Queue SSD devices." 16th USENIX Conference on File and Storage Technologies (FAST 18). 2018. Paper Link Git