ClickHouse Introduction and Deep Dive

  时 间:2019年6月11日(周二)下午14:00

  地 点:计算所446会议室

  报告人:Alexey Milovidov from Yandex

  ClickHouse Project Founder and Core Developer

  摘要:ClickHouse is an open source analytical database management system with SQL support. It is capable of storing tens of petabytes of data and processing billions of rows per second per server to provide analytical reports with subsecond latencies, all while ingesting new data in real-time. ClickHouse was originally built by Yandex and nowadays it is used by hundreds of companies including Tencent, Sina, TouTiao, Huya, KuaiShou, Qingyun and CloudFlare. In this lecture, we will first give an overview of what ClickHouse is, how it works and how with iterative approach to organizing data storage it resulted to be a powerful and extremely fast open source system. Then we will present a subset of the most notable ClickHouse features introduced recently, such as data skipping indices, custom compression codecs, sampling profiler on the query level and z-curve indexing, etc. Finally, we will talk about ClickHouse internal design and unique implementation details that allow us to achieve the maximum performance of query processing and data storage efficiency.

  报告人简介:Alexey Milovidov is graduated from Moscow State Unversity, department of Mechanics and Mathematics with specialist degree, mathematician in year 2008. Since then he works for Yandex LLC, leading either the Yandex Metrica (Similar to Google Analytics and Baidu Tongji) engine development team and the ClickHouse development team. He has 11 years experience with development of specialized data structures using C++ programming language.