Introduction Persistent Hash Map Persistent Transactional Data Structures Live Demonstration ReferencesIntroduction Persistent Hash Map Persistent Transactional Data Structures Live Demonstration References Persistent Hash Map Design Goals and Methodology Persistence Performance Results Persistent Transactional Data Structures Design Goals Methodology Performance Results Live Demonstration A Persistent Processing Workloads and a Methodology for Persistent Transactional Data Structures 2IntroductionIntroduction Persistent Hash Map Persistent Transactional Data Structures Live Demonstration References Introduction

Timestamp Ordering (STO) • STO is one of many database concurrency control algorithms • It is a transactional, timestamp-based algorithm • Timestamp • A monotonically increasing value that indicates the Measure multi-threaded updates guarded by a single critical section • Measure multi-threaded transactional updates • 8-Core (16 hypercores), Ubuntu 18.04, GCC 10.2 CppCon 2020 - A Multi-threaded, Transaction-Based fprintf(fp, "RACE FOUND!, TX %zd item %zd\n", tx.id(), this->id()); } }Copyright © 2020 Bob Steagall Transactional Element Access Test 110 CppCon 2020 - A Multi-threaded, Transaction-Based Locking Strategy for

and Notifications, which de- scribed Percolator: a Google-internal database for ran- dom access transactional workloads where low laten- cies are not required. Percolator uses a global co- ordination service timestamps and coordinates shards • TiKV: a sharded, horizontally-scalable key-value store • TiDB: a transactional SQL layer which stores data in TiKV Placement Driver is replicated via the Raft consensus algorithm linearizability) allow the verification of arbitrary histories. However, our usual tests for transactional systems rely on a care- fully selected “artisanal” set of transactions with hand- proven invariants

· · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · 6724 17.6.1 Hybrid Transactional and Analytical Processing (HTAP) · · · · · · · · · · · · 6724 17.7 I · · · · · · · · · · · · (/’ta￿di￿bi:/, “Ti” stands for Titanium) is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability The goal of TiDB is to provide users with a one-stop database solution that covers OLTP (Online Transactional Processing), OLAP (Online Analytical Processing), and HTAP services. TiDB is suitable for various

(/’ta￿di￿bi:/, “Ti” stands for Titanium) is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability The goal of TiDB is to provide users with a one-stop database solution that covers OLTP (Online Transactional Processing), OLAP (Online Analytical Processing), and HTAP services. TiDB is suitable for various as a true HTAP database. With a small amount of extra storage cost, you can handle both online transactional processing and real-time data analysis in the same system, which greatly saves cost. • Data aggregation

(/’ta￿di￿bi:/, “Ti” stands for Titanium) is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability The goal of TiDB is to provide users with a one-stop database solution that covers OLTP (Online Transactional Processing), OLAP (Online Analytical Processing), and HTAP services. TiDB is suitable for various as a true HTAP database. With a small amount of extra storage cost, you can handle both online transactional processing and real-time data analysis in the same system, which greatly saves cost. • Data aggregation

(/’ta￿di￿bi:/, “Ti” stands for Titanium) is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability The goal of TiDB is to provide users with a one-stop database solution that covers OLTP (Online Transactional Processing), OLAP (Online Analytical Processing), and HTAP services. TiDB is suitable for various as a true HTAP database. With a small amount of extra storage cost, you can handle both online transactional processing and real-time data analysis in the same system, which greatly saves cost. • Data aggregation

(/’ta￿di￿bi:/, “Ti” stands for Titanium) is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability The goal of TiDB is to provide users with a one-stop database solution that covers OLTP (Online Transactional Processing), OLAP (Online Analytical Processing), and HTAP services. TiDB is suitable for various as a true HTAP database. With a small amount of extra storage cost, you can handle both online transactional processing and real-time data analysis in the same system, which greatly saves cost. • Data aggregation

using the MySQL code base ● It would be cool to do some lightweight OLAP queries directly on the transactional database. ○ No need to involve data warehouse! ○ Example: a dashboard for each tenant in SaaS Physical Stack Highly layered TiKV API (gRPC) Transaction MVCC Multi-Raft (gRPC) RocksDB Raw KV API Transactional KV API TiKV Node Store 1 Region 1 Region 2 Region 3 Region 4 Local RocksDB instance t1_r1

论文启发而设计的开源分布式 HTAP (Hybrid Transactional and Analytical Processing) 数据库，结合了传统的 RDBMS 和 NoSQL 的最佳特性。 TiDB 兼容 MySQL，支持无限的水平扩展，具备强一致性和高可用性。TiDB 的目标是为 OLTP (Online Transactional Processing) 和 OLAP (Online 论文启发而设计的开源分布式 HTAP (Hybrid Transactional and Analytical Processing) 数据库，结合了传统的 RDBMS 和 NoSQL 的最佳特性。 TiDB 兼容 MySQL，支持无限的水平扩展，具备强一致性和高可用性。TiDB 的目标是为 OLTP (Online Transactional Processing) 和 OLAP (Online 论文启发而设计的开源分布式 HTAP (Hybrid Transactional and Analytical Processing) 数据库，结合了传统的 RDBMS 和 NoSQL 的最佳特性。 TiDB 兼容 MySQL，支持无限的水平扩展，具备强一致性和高可用性。TiDB 的目标是为 OLTP (Online Transactional Processing) 和 OLAP (Online