Key-Space Partitioned LSM Tree for CMM-H
Authors:
- 21 August 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
The Log-Structured Merge Tree (LSM Tree) is widely employed in key-value stores, ensuring efficient database read performance at the expense of increased write stall. While this stall enhances read performance, it notably degrades write efficiency. This paper examines the write stall phenomenon in LSM Tree-based key-value stores and proposes a solution: Key Space Partitioned RocksDB. This architecture comprises a MemTable backed by Storage DRAM, the Key Space Partitioned MemTable, and the Key Space Partitioned LSM Tree. Key Space Partitioned RocksDB demonstrates a $1.7\times$ enhancement in YCSB-A throughput compared to conventional RocksDB, a $3.5\times$ reduction in average GET(key) latency, and a $1.2 \times$ decrease in average PUT (key, value) latency.
Keywords
Funding Information
- NRF, Korea (NRF-2020R1A2C3008525)
This publication has 8 references indexed in Scilit:
- Hello bytes, bye blocks2022
- LinkBench2013
- Workload analysis of a large-scale key-value store2012
- bLSM2012
- CassandraACM SIGOPS Operating Systems Review, 2010
- BigtableACM Transactions on Computer Systems, 2008
- DynamoACM SIGOPS Operating Systems Review, 2007
- The log-structured merge-tree (LSM-tree)Acta Informatica, 1996