基于LSM-Tree的键值存储系统的读写性能优化
Read and Write Performance Optimization of Storage System Based on LSM-tree Key Value
程浩津 1胡乃平1
作者信息
- 1. 青岛科技大学信息科学技术学院,山东青岛 266061
- 折叠
摘要
在写密集型工作环境中,日志结构合并树(LSM-Tree)已逐渐成为主流存储系统,LSM-Tree存在读操作速度慢、写操作成本高、范围查询操作效率低等问题;针对这些问题,为提升LSM-Tree的性能进行了研究,提出了一种基于LSM-Tree的键值存储系统的读写性能优化策略,通过键值分离策略设计vTree结构,并提出层内归并与消极的层间合并相结合的方法,以及范围查询优化合并的策略,从而优化系统的范围查询性能,在LSM-Tree和vTree采用不同的压缩结构,以实现系统读写性能的提升;实验结果表明,与RocksDB相比读性能提升30％,与RocksDB-vTree相比范围查询性能提升10％.
Abstract
In a write-intensive work environment,log-structured-merge(LSM-Tree)has gradually become a mainstream storage system,there are problems in LSM-tree such as slow read operation speed,high cost of write operation,and low efficiency of range query operation,etc.In view of these problems,this paper presents a study to improve the performance of LSM-tree,and optimize the read and write performance of key-value storage system based on LSM-tree,and proposes a read and write performance optimiza-tion strategy for LSM-tree-based key-value storage system,designs the vTree structure through the key-value separation strategy,and presents the combination of layer merging and negative inter layer merging,as well as the strategy of range query-optimized merging,so as to optimize the range query performance of the system,and adopt different compression structures in the LSM-tree and vTree to improve the system's read and write performance;the experimental results show that the read performance is improved by 30％compared with the RocksDB system,and the range query performance is improved by 10％compared with the RocksDB-vTree system.
关键词
读性能/LSM-Tree/消极的层间合并/范围查询优化合并/范围查询Key words
read performance/LSM-Tree/negative cascade consolidation/range query optimization merge/scope query引用本文复制引用
出版年
2024
NETL
NSTL
万方数据