KVSSD:结合 LSM 与 FTL 以实现写入优化 的 KV 存储|DB Paper Reading 线上直播
DB Paper Reading 这周继续来营业啦!我们希望通过对业界学术论文的分享,带大家了解数据库学术界最新的研究方向。8 月 31 日晚青云存储工程师 xuanwo 将为大家解读论文 KVSSD: Close integration of LSM trees and flash translation layer for write-efficient KV store,在该论文的基础上,与大家分享业界关于 NVMe 的进展,介绍 KV-SSD 接口。感兴趣的朋友不要错过,赶紧报名约起来~
直播季
PingCAP Paper Reading
时间:2021 年 8 月 31 日晚 19:00-20:00
19:00 - 20:00
KVSSD: Close integration of LSM trees and flash translation layer for write-efficient KV store

丁皓/xuanwo
青云存储工程师
个人博客:xuanwo.io
Content:
这篇 Paper 主要思路是 SSD 上直接提供 KV 接口,将 LSM Tree 与 FTL 深度结合,从而避免从 LSM Tree,主机文件系统到 FTL 多个软件层的写入放大。
Log-Structured-Merge (LSM) trees are a write-optimized data structure for lightweight, high-performance Key-Value (KV) store. Solid State Disks (SSDs) provide acceleration of KV operations on LSM trees. However, this hierarchical design involves multiple software layers, including the LSM tree, host file system, and Flash Translation Layer (FTL), causing cascading write amplifications. We propose KVSSD, a close integration of LSM trees and the FTL, to manage write amplifications from different layers. KVSSD exploits the FTL mapping mechanism to implement copy-free compaction of LSM trees, and it enables direct data allocation in flash memory for efficient garbage collection. In our experiments, compared to the hierarchical design, our KVSSD reduced the write amplification by 88% and improved the throughput by 347%.
报名方式:扫描二维码即可参与报名~
关注公众号:拾黑(shiheibook)了解更多 [广告]赞助链接:
四季很好,只要有你,文娱排行榜:https://www.yaopaiming.com/
让资讯触达的更精准有趣:https://www.0xu.cn/

随时掌握互联网精彩
- 1 为实现中国梦强军梦汇聚强大力量 7903987
- 2 中国取消1.2万吨美国猪肉订单 7807999
- 3 复旦回应拟录取600万粉丝网红 7713373
- 4 美国关税“后坐力”显现 7618754
- 5 日本东京有8.3级大地震?专家回应 7523866
- 6 中国贸易摩擦进入高强度阶段 7423839
- 7 63岁徐锦江已向儿子交代后事 7330152
- 8 中央巡视组进驻四川 首虎落马 7235696
- 9 纽约市民凌晨排队抢购中国全景相机 7136668
- 10 赵露思下车动作惹争议 7043419