All-Flash Array Key-Value Cache for Large Objects
Open Access
- 8 May 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 784-799
Abstract
We present BigKV, a key-value cache specifically designed for caching large objects in an all-flash array (AFA). The design of BigKV is centered around the unique property of a cache: since it contains a copy of the data, exact bookkeeping of what is in the cache is not critical for correctness. By ignoring hash collisions, approximating metadata information, and allowing data loss from failures, BigKV significantly increases the cache hit ratio and keeps more useful objects in the system. Experiments on a real AFA show that our design increases the throughput by 3.1× on average and reduces the average and tail latency by 57% and 81%, respectively.Keywords
Funding Information
- National Research Foundation of Korea (NRF-2018R1A5A1060031, NRF-2020R1A4A4079859)
- National Science Foundation (CNS-2008453)
- Ministry of Trade, Industry and Energy (1415181081)
- Korea Semiconductor Research Consortium (20019402)
This publication has 23 references indexed in Scilit:
- KV-Direct2017
- The Unwritten Contract of Solid State Drives2017
- A High Performance Storage Appliance for Genomic Data2017
- BluecacheProceedings of the VLDB Endowment, 2016
- Does RAID Improve Lifetime of SSD Arrays?ACM Transactions on Storage, 2016
- Three-Dimensional 128 Gb MLC Vertical nand Flash Memory With 24-WL Stacked Layers and 50 MB/s High-Speed ProgrammingIEEE Journal of Solid-State Circuits, 2014
- An efficient design and implementation of LSM-tree based key-value store on open-channel SSD2014
- Benchmarking cloud serving systems with YCSB2010
- CassandraACM SIGOPS Operating Systems Review, 2010
- Introduction to flash memoryProceedings of the IEEE, 2003