VLDB（International Conference on Very Large Data Bases）是数据库三大国际顶级学术会议之一，属于CCF A类，CORE Computer Science Conference Rankings A+类会议，每届会议都设有研究（Research Track）、工业（Industrial Track）等方向，展示了当前数据库领域的前沿方向以及工业界最新的技术进展。
VLDB 2024是VLDB举办50周年，将于8月26-30日在中国广州举行。大会期间，敬请关注云原生数据库相关研讨会及论文宣讲：- Workshop: Industry Challenge and Vision Workshop
- Sponsor Talk: Continuous Architecture Evolution in Cloud-native GaussDB
- 论文宣讲：《GaussDB: A Cloud-Native Multi-Primary Database with Compute-Memory-Storage Disaggregation》
云原生数据库旨在充分利用云基础设施的强大功能，提供动态可扩展性、高效资源管理以及与云服务的无缝集成。随着大语言模型的出现，数据库的高性能和高弹性得到了进一步增强。云原生数据库技术与大语言模型的融合为更直观、更强大、更易访问的数据服务铺平了道路。
为了应对这一行业趋势带来的技术挑战，本次研讨会将采用圆桌会议的形式。由香港科技大学陈雷教授、SFU王健楠教授、SFU王添正助理教授、华为公司曾凯、香港科技大学周晓方教授等五位数据库领域专家共同组织。每场会议将以一场演讲开始，重点介绍行业实践中遇到的研究问题，然后就潜在的解决方案进行公开讨论。旨在为研究人员和从业者提供一个平台，让他们交流思想，分享正在进行的工作。
Industry Challenge and Vision Workshop⏰ 时间：8 月 26 日 09:00-17:30
📍 地点：广州朗豪酒店 3F Great Hall Foyer
🔗 网址：https://db-challenge-vision.github.io/
Sponsor Talk: Continuous Architecture Evolution in Cloud-native GaussDB
⏰ 时间：8 月 27 日 11:00-12:30📍 地点：广州朗豪酒店 会议厅Great Hall D2🎙️ 嘉宾：华为爱丁堡研究所专家 Nikolaos Ntarmos
嘉宾简介：Dr Nikos Ntarmos is the Director of the Database Lab at Huawei's Edinburgh Research Centre. His research interests lie in the areas of distributed computing and (large-scale) data management systems, with a focus on issues pertaining to storage, indexing and query processing and optimization, in embedded databases, distributed data stores, multi-model databases, geo-distributed data management infrastructures, and joint at-rest/streaming data processing systems. He received his PhD in computer engineering and informatics from the University of Patras in 2008, is a member of the IEEE and the ACM, and a Fellow of the UK Higher Education Academy. Before joining Huawei, he held academic posts at the University of Glasgow and the University of Ioannina, and research fellow posts at the University of Glasgow and the University of Patras. He was a recipient of the best paper award at the ACM CIKM 2006 conference and the best student paper award at the IEEE Big Data 2018 conference, and has published at and served in the Program Committees of multiple international conferences (including VLDB, SIGMOD, ICDE, Middleware, etc.).
VLDB每年的论文录用率在18%左右，对作品的创新性、完整性、实验设计等方面要求十分严格，因此每篇录用论文质量都非常高，对于推动数据驱动决策、智能系统演进、应用创新等具有重要意义。华为11篇论文入选VLDB 2024：
Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index Advisors
A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation LearningSepHash: A Write-Optimized Hash Index On Disaggregated Memory via Separate Segment StructureFusionQuery: On-demand Fusion Queries over Multi-source Heterogeneous DataHost Profit Maximization: Leveraging Performance Incentives and User FlexibilityCoroGraph: Bridging Cache Efficiency and Work Efficiency for Graph Algorithm ExecutionNeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph StreamsTFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting MethodsGaussDB: A Cloud-Native Multi-Master Database with Compute-Memory-Storage DisaggregationUniView: A Unified Autonomous Materialized View Management System for Various DatabasesOptimizing Distributed Tiered Data Storage Systems with DITIS
此处将对云原生数据库论文《GaussDB: A Cloud-Native Multi-Master Database with Compute-Memory-Storage Disaggregation》进行简要介绍，同时该论文将在VLDB 2024会议期间进行宣讲。
本篇论文介绍了GaussDB云原生数据库的架构和设计原理, 主要包括在三层池化架构下分布式缓冲池的本地亲和性读写、智能路由、分布式锁、事务处理等技术以及通过Lamport CSN和Lamport LSN实现计算节点透明多写能力。通过基于内存和磁盘双检查点，Past Image机制，按需恢复页面等故障恢复设计，实现节点故障期间，存活计算节点业务不中断，持续运行，达到极致RTO。同时，还介绍了基于BUCKET粒度的一致性哈希算法，实现了内存节点的在线弹性扩展能力, 而在线添加计算节点不需要 pd 和lock bucket迁移，几乎无任何影响, 达到类似serverless效果。⏰ 时间：8 月 27 日 11:00-12:30📍 地点：3F Great Hall Foyer B1会场此次论文的入选，既是华为在数据库领域持续创新、研发投入的成果，也是华为长期坚持产、学、研、用深度融合的体现。未来，华为将继续加大数据库技术领域的投入，在数据库领域持续创新，将论文理论转化成应用落地，为客户提供创新且有竞争力的数据库产品和服务，推动数据库技术的进步与发展。
华为云数据库特惠
F产品新客免费试用1个月，1年180元起
扫码抢购
戳“阅读原文”，了解更多
