Freeing the Power of High Parallelism: Accelerating the Bϵ-Tree Indexing Scheme Performance on Open-Channel SSD

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：1

、訪客IP：3.17.128.129

姓名

邱麒亮(Chi-Liang Qiu) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

(Freeing the Power of High Parallelism: Accelerating the Bϵ-Tree Indexing Scheme Performance on Open-Channel SSD)

相關論文

★ 重新思考虛擬記憶體管理的方式以開放通道式固態硬碟最大限度地減少深度學習推薦系統演算法的讀寫流量	★ 開啟製程相似檢查方法在組裝超級塊上以最小化額外的寫入延遲
★ LaDy: Enabling Locality-aware Deduplication Technology on Shingled Magnetic Recording Drives	★ On Minimizing Writing Overhead to Establish a Low-latency LSM-tree on Skyrmion-based Racetrack Memory
★ WABE: Rethinking B-epsilon-tree to Minimize Write-amplification on NAND Flash Memory	★ Rethinking Bϵ tree Indexing Structure over NVM with the Support of Multi-write Modes
★ Prophet’s Insight: Unleashing Deduplication System Performance in Multi-tier Storage Systems	★ Applying Content-Defined Chunking to OCSSD-based Deduplication Systems
★ GraLoc: Preserving Graph Locality to Minimize Read and Write Amplification on NAND Flash Memory	★ On Minimizing Writing Overhead to Establish a Low-latency LSM-tree on Skyrmion-based Racetrack Memory

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2026-7-25以後開放)

摘要(中)

Bϵ-樹在寫入密集的情況下，是一個很好的選擇，他將多個寫入請求合併到緩衝區，
這有助於減少寫入放大。SplinterDB [1] 是以Bϵ-樹實作而成，且配合了NVMe 裝置，然
而，他並不是為了開放通道式固態硬碟，我們提出了高度平行Bϵ-樹，他可以很好的利用
開放式固態硬碟有，而傳統固態硬碟沒有的優勢，在我們的論文中，提出一個方法，藉由
維持高度平行讀取，使得讀取延遲下降。

摘要(英)

Bϵ-tree is a good candidate for write-intensive situations. It gathers multiple
write requests into its buffer. This helps reduce write amplification (WA).
SplinterDB [1] is implemented using Bϵ-trees and is compatible with NVMe
solid-state drives[1]. However, it’s not designed for open-channel SSDs[2].
We designed HP-Bϵ-tree to leverage the advantages of open-channel SSDs
over traditional SSDs. In this paper, we propose an approach to reduce read
latency by maintaining high degree of parallel reads.

關鍵字(中)

★ Bϵ-樹
★ 開放通道式固態硬數
★ 鍵值儲存

關鍵字(英)

★ Bϵ-tree
★ Open-channel SSD
★ key-value store

論文目次

中文摘要 iv
英文摘要 v
目次 vi
1. Introduction 1
2. Background and Motivation 3
2.1 Bϵ-tree 3
2.2 OCSSD (Open-Channel SSD) 7
2.3 Motivation 10
3. Hp-Bϵ-tree 13
3.1 Factors We Take into Consideration 13
3.2 Definition of the Maximum Network Flow Problem 16
3.3 Problem Reduced 17
3.4 Further Optimized Design 20
4. Implementation Details 23
5. Evaluation 25
6. Conclusion 29

參考文獻

1. Alex Conway, Abhishek Gupta, Vijay Chidambaran, Martin Farach-
Colton, Rick Spillane, Amy Tai, and Rob Johnson. 2020. SplinterDB:
closing the bandwidth gap for NVMe key-value stores. In Proceedings of
the 2020 USENIX Conference on Usenix Annual Technical Conference
(USENIX ATC’20). USENIX Association, USA, Article 4, 49–63.

2. Bjørling, Matias et al. “LightNVM: The Linux Open-Channel SSD Subsystem.”
USENIX Conference on File and Storage Technologies (2017).

3. Bender, Michael A. et al. “An Introduction to Bϵ-trees and Write-Optimization.”login Usenix Mag. 40 (2015): n. pag.

4. Peng Wang, Guangyu Sun, Song Jiang, Jian Ouyang, Shiding Lin, Chen
Zhang, and Jason Cong. 2014. An efficient design and implementation of LSM-tree based key-value store on open-channel SSD. In Proceedings of the Ninth European Conference on Computer Systems (EuroSys ’14). Association for Computing Machinery, New York, NY, USA, Article 16, 1–14. https://doi.org/10.1145/2592798.2592804

5. S. -M. Wu, K. -H. Lin and L. -P. Chang, ” Integrating LSM Trees With Multichip Flash Translation Layer for Write-Efficient KVSSDs,” in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 40, no. 1, pp. 87-100, Jan. 2021, doi: 10.1109/ TCAD.2020.2987781.

6. Jiacheng Zhang, Youyou Lu, Jiwu Shu, and Xiongjun Qin. 2017. FlashKV: Accelerating KV Performance with Open-Channel SSDs. ACM Trans. Embed. Comput. Syst. 16, 5s, Article 139 (October 2017), 19 pages.https://doi.org/10.1145/3126545

7. Jingpei Yang, Ned Plasson, Greg Gillis, Nisha Talagala, Swaminathan Sundararaman SanDisk Corporation Don’t stack your Log on my Log

8. Jannen, William et al. “BetrFS: A Right-Optimized Write-Optimized File System.”USENIX Conference on File and Storage Technologies (2015).

9. Open-Channel Solid State Drives Specification http://lightnvm.io/docs/OCSSD-2 0-20180129.pdf

10. https://www.cs.cmu.edu/~15451-f22/lectures/lec11-flow1.pdf

11. https://www.ics.uci.edu/~goodrich/teach/cs165/notes/BinPacking.pdf

12. https://dev.mysql.com/doc/refman/8.0/en/innodb-physical-structure.html

13. https://github.com/google/leveldb

指導教授

陳增益(Tseng-Yi Chen)

審核日期

2023-8-17

推文