ClickHouse是俄罗斯第一大搜索引擎Yandex开发的列式储存数据库.令人惊喜的是,这个列式储存数据库的性能大幅超越了很多商业MPP数据库软件,比如Vertica,InfiniDB.
相比传统的数据库软件,ClickHouse要快100-1000X:
100Million 数据集:
-
ClickHouse比Vertica约快5倍,比Hive快279倍,比My SQL快801倍
1Billion 数据集:
-
ClickHouse比Vertica约快5倍,MySQL和Hive已经无法完成任务了
该项目当前还有一些不足:
-
pre-build包只有Ubuntu平台的可用,并且该项目当前没有任何架构文档
-
只有Github上面的C++源代码
主要功能
-
True column-oriented
-
Vectorized query execution
-
Data compression
-
Parallel and distributed query execution
-
Real-time data ingestion
-
On-disk locality of reference
-
Real-time query processing
-
Cross-datacenter replication
-
High availability
-
SQL support
-
Local and distributed joins
-
Pluggable external dimension tables
-
Arrays and nested data types
-
Approximate query processing
-
Probabilistic data structures
-
Full support of IPv6
-
Features for web analytics
-
State-of-the-art algorithms
-
Detailed documentation
-
Clean documented code
应用场景
-
Web and App analytics
-
Advertising networks and RTB
-
Telecommunications
-
E-commerce
-
Information security
-
Monitoring and telemetry
-
Business intelligence
-
Online games
-
Internet of Things
评论