数据库/分布式系统资源合集

Confereence/Talks/Meetings

• PGCon - 可以在每一年的Events中下载演讲Slides

Courses

• CMU15721
• CMU15445

Papers

• Amazon Aurora, 一个通过将MySQL数据库中的redolog抽离为独立的存储服务从而提高系统吞吐量的云原生数据库
  • Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases [翻译]
  • Amazon Aurora: On avoiding distributed consensus for I/Os, commits, and membership changes
• Dynamo - Dynamo: Amazon’s Highly Available Key-value Store
• Spanner
  • Spanner: Google’s Globally-Distributed Database
  • Spanner: Becoming a SQL System
• F1
  • F1: A Distributed SQL Database That Scales CMU ppt
  • Online, Asynchronous Schema Change in F1
  • F1 Query: Declarative Querying at Scale
• 执行引擎/Pipeline调度
  • 技术内幕 | StarRocks Pipeline 执行框架（上）
  • 技术内幕 | StarRocks Pipeline 执行框架（下）
  • OLAP 任务的并发执行与调度
  • ClickHouse之Pipeline执行引擎(持续更新)
  • ClickHouse Query Execution Pipeline
  • Push还是Pull，这是个问题么？
  • Morsel-Driven Parallelism: A NUMA-Aware Query Evaluation Framework for the Many-Core Age
  • Self-Tuning Query Scheduling for Analytical Workloads
• Turbine - Turbine: Facebook’s Service Management Platform for Stream Processing
• Hologres - Alibaba Hologres: A Cloud-Native Service for Hybrid Serving/Analytical Processing
• Snowflake - The Snowflake Elastic Data Warehouse
• DuckDB
  • DuckDB: an Embeddable Analytical Database
  • Data Management for Data Science Towards Embedded Analytics
• Velox - Velox: Meta’s Unified Execution Engine
• Photon - Photon: A Fast Query Engine for Lakehouse Systems [解读]
• PolarFS - PolarFS: An Ultra-low Latency and Failure Resilient Distributed File System for Shared Storage Cloud Database [解读]
• 阿里盘古 - More Than Capacity: Performance-oriented Evolution of Pangu in Alibaba
• OceanBasee - OceanBase: A 707 Million tpmC Distributed Relational Database System
• 虚拟共识，Delos通过对不同的共识协议作进一步抽象，在复制状态机WAL日志和数据库之间增加一层虚拟日志层，使得上层应用不感知具体的共识协议的实现，从而支持多种共识协议共存，共识协议热替换等功能
  • Virtual Consensus in Delos 论文解读
• Log-Structured, 一个分层复制状态机的协议，它规定了层与层之间的接口与交互方式。通过这个协议，我们可以将业务罗即拆分为多个engine，再通过堆叠的方式构建应用，从而提高了组件的复用性和应用的可拓展性。
  • READING GROUP. LOG-STRUCTURED PROTOCOLS IN DELOS 论文解读
• Apache Kudu - Kudu: Storage for Fast Analytics on Fast Data
• FoundationDB - FoundationDB: A Distributed Unbundled Transactional Key Value Store
  • 其中控制面使用Active Disk Paxos来达到高可用
• ByteHTAP - ByteHTAP: ByteDance’s HTAP System with High Data Freshness and Strong Data Consistency [解读]
• ByteKV - 赌你看不懂：分布式存储系统的数据强一致性挑战
• Krypton - Krypton: Real-time Serving and Analytical SQL Engine at ByteDance
• PebblesDB - PebblesDB: Building Key-Value Stores using Fragmented Log-Structured Merge Trees
• Fast Scans on Key-Value Stores
• Removing Double-Logging with Passive Data Persistence in LSM-tree based Relational Databases
• Enhancing RocksDB for Speed & Scale
• TiFlash 源码阅读