TierBase: A Workload-Driven Cost-Optimized Key-Value Store

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Zhitao, Yang, Shiyu, Chen, Weibo, Wang, Kunming, Li, Yue, Jin, Jiabao, Jia, Wei, Chen, Junwei, Su, Yuan, Duan, Xiaoxia, Chen, Wei, Wang, Lei, Song, Jie, Ruan, Ruoyi, Lin, Xuemin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909606447415296
author Shen, Zhitao
Yang, Shiyu
Chen, Weibo
Wang, Kunming
Li, Yue
Jin, Jiabao
Jia, Wei
Chen, Junwei
Su, Yuan
Duan, Xiaoxia
Chen, Wei
Wang, Lei
Song, Jie
Ruan, Ruoyi
Lin, Xuemin
author_facet Shen, Zhitao
Yang, Shiyu
Chen, Weibo
Wang, Kunming
Li, Yue
Jin, Jiabao
Jia, Wei
Chen, Junwei
Su, Yuan
Duan, Xiaoxia
Chen, Wei
Wang, Lei
Song, Jie
Ruan, Ruoyi
Lin, Xuemin
contents In the current era of data-intensive applications, the demand for high-performance, cost-effective storage solutions is paramount. This paper introduces a Space-Performance Cost Model for key-value store, designed to guide cost-effective storage configuration decisions. The model quantifies the trade-offs between performance and storage costs, providing a framework for optimizing resource allocation in large-scale data serving environments. Guided by this cost model, we present TierBase, a distributed key-value store developed by Ant Group that optimizes total cost by strategically synchronizing data between cache and storage tiers, maximizing resource utilization and effectively handling skewed workloads. To enhance cost-efficiency, TierBase incorporates several optimization techniques, including pre-trained data compression, elastic threading mechanisms, and the utilization of persistent memory. We detail TierBase's architecture, key components, and the implementation of cost optimization strategies. Extensive evaluations using both synthetic benchmarks and real-world workloads demonstrate TierBase's superior cost-effectiveness compared to existing solutions. Furthermore, case studies from Ant Group's production environments showcase TierBase's ability to achieve up to 62% cost reduction in primary scenarios, highlighting its practical impact in large-scale online data serving.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06556
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TierBase: A Workload-Driven Cost-Optimized Key-Value Store
Shen, Zhitao
Yang, Shiyu
Chen, Weibo
Wang, Kunming
Li, Yue
Jin, Jiabao
Jia, Wei
Chen, Junwei
Su, Yuan
Duan, Xiaoxia
Chen, Wei
Wang, Lei
Song, Jie
Ruan, Ruoyi
Lin, Xuemin
Databases
Distributed, Parallel, and Cluster Computing
In the current era of data-intensive applications, the demand for high-performance, cost-effective storage solutions is paramount. This paper introduces a Space-Performance Cost Model for key-value store, designed to guide cost-effective storage configuration decisions. The model quantifies the trade-offs between performance and storage costs, providing a framework for optimizing resource allocation in large-scale data serving environments. Guided by this cost model, we present TierBase, a distributed key-value store developed by Ant Group that optimizes total cost by strategically synchronizing data between cache and storage tiers, maximizing resource utilization and effectively handling skewed workloads. To enhance cost-efficiency, TierBase incorporates several optimization techniques, including pre-trained data compression, elastic threading mechanisms, and the utilization of persistent memory. We detail TierBase's architecture, key components, and the implementation of cost optimization strategies. Extensive evaluations using both synthetic benchmarks and real-world workloads demonstrate TierBase's superior cost-effectiveness compared to existing solutions. Furthermore, case studies from Ant Group's production environments showcase TierBase's ability to achieve up to 62% cost reduction in primary scenarios, highlighting its practical impact in large-scale online data serving.
title TierBase: A Workload-Driven Cost-Optimized Key-Value Store
topic Databases
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2505.06556