Dhcache: a dual-hash cache for optimizing the read performance in key-value store

被引:0
作者
Lu, Jinkang [1 ,2 ,3 ]
Lv, Meng [4 ]
Li, Peixuan [1 ,2 ,3 ]
Yuan, Zhu [5 ]
Xie, Ping [1 ,2 ,3 ]
机构
[1] Qinghai Normal Univ, Sch Comp, Xining 810016, Peoples R China
[2] Key Lab Internet Things Qinghai Prov, Xining 810016, Peoples R China
[3] State Key Lab Tibetan Intelligent Informat Proc &, Xining 810016, Peoples R China
[4] Qingdao Tech Coll, Informat & Technol Ctr, Qingdao 266555, Peoples R China
[5] Natl Police Univ Criminal Justice, Dept Informat Management, Baoding 071000, Peoples R China
基金
中国国家自然科学基金;
关键词
Key-value store; Cache; Hash table; Cache replacement policy;
D O I
10.1007/s11227-024-06828-w
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Key-value (KV) stores are widely utilized in data-intensive applications to obtain exceptional storage performance. However, its caching mechanism often suffers read and write pauses. Especially when accessing old data periodically, it results in cache hit ratios and system throughput decline. To address the performance degradation issue, we propose an innovative dual-hash caching mechanism called DHCache. Firstly, we introduce a dual-hash structure in DHCache. It alleviates read and write pauses by reducing the frequency of rehash operations on the hash table. Secondly, we employ a Most Recently Used (MRU) cache replacement policy on DHCache to retain old data. This enhances the cache hit ratios and throughput when periodically accessing old data. DHCache is deployed within LevelDB, demonstrating significant performance advantages. Experimental results indicate that DHCache improves throughput by 11.89-21.92% in various read workloads compared to traditional LRUCache. Significantly, read performance improvement does not come at the cost of write performance degradation.
引用
收藏
页数:26
相关论文
共 48 条
  • [1] Maintaining Dimension's History in Data Warehouses Effectively
    Atay, Canan Eren
    Garani, Georgia
    [J]. INTERNATIONAL JOURNAL OF DATA WAREHOUSING AND MINING, 2019, 15 (03) : 46 - 62
  • [2] Window-LRFU: a cache replacement policy subsumes the LRU and window-LFU policies
    Bai, Sen
    Bai, Xin
    Che, Xiangjiu
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2016, 28 (09) : 2670 - 2684
  • [3] Baker Mary., 2005, Proc. 1st IEEE Workshop on Hot Topics in System Dependability, P2005
  • [4] Bender MA, 2023, Arxiv, DOI arXiv:2304.04954
  • [5] Using Simulation to Design Scalable and Cost-Efficient Archival Storage Systems
    Byron, James
    Long, Darrell D. E.
    Miller, Ethan L.
    [J]. 2018 IEEE 26TH INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS, AND SIMULATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS (MASCOTS), 2018, : 25 - 39
  • [6] Bigtable: A distributed storage system for structured data
    Chang, Fay
    Dean, Jeffrey
    Ghemawat, Sanjay
    Hsieh, Wilson C.
    Wallach, Deborah A.
    Burrows, Mike
    Chandra, Tushar
    Fikes, Andrew
    Gruber, Robert E.
    [J]. ACM TRANSACTIONS ON COMPUTER SYSTEMS, 2008, 26 (02):
  • [7] PARC: A novel OS cache manager
    Chang, Hsung-Pin
    Chiang, Cheng-Pang
    [J]. SOFTWARE-PRACTICE & EXPERIENCE, 2018, 48 (12) : 2193 - 2222
  • [8] Realtime Data Processing at Facebook
    Chen, Guoqiang Jerry
    Wiener, Janet L.
    Iyer, Shridhar
    Jaiswal, Anshul
    Lei, Ran
    Simha, Nikhil
    Wang, Wei
    Wilfong, Kevin
    Williamson, Tim
    Yilmaz, Serhat
    [J]. SIGMOD'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2016, : 1087 - 1098
  • [9] Chen JQ, 2020, PROCEEDINGS OF THE 18TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES, P239
  • [10] Cooper B F, 2010, Proceedings of the 1st ACM symposium on Cloud computing, SoCC '10, P143, DOI DOI 10.1145/1807128.1807152