O'Reilly、Cloudera 主办
Make Data Work
2017年7月12-13日:培训
2017年7月13-15日:会议
北京,中国

生产环境里的堆外内存HBase读路径——阿里巴巴的故事 (Off-heap HBase read path in production: The Alibaba story)

This will be presented in English.

Yu Li (Alibaba), Ramkrishna Vasudevan (Intel)
14:00–14:40 Friday, 2017-07-14
Hadoop内核&发展 (Hadoop internals & development), 英文讲话 (Presented in English)
地点: 多功能厅6A+B(Function Room 6A+B) 观众水平 (Level): Advanced
平均得分:: ***..
(3.00, 1 次得分)

必要预备知识 (Prerequisite Knowledge)

A working knowledge of HBase and Java

您将学到什么 (What you'll learn)

Understand how to achieve better throughput with read-path off-heaping in HBase and learn how Alibaba met the challenge of serving high throughput on 2016 Singles' Day

描述 (Description)

阿里巴巴使用HBase提供实时搜索索引更新,也作为在线机器学习系统的数据存储系统。阿里巴巴的HBase集群包括1500多个节点和20万个以上的区域,对它维持一致的延迟和吞吐量是非常有挑战性的。 使用堆外内存HBase读路径,我们将吞吐量提高了30%,并取得了可预测的延迟。 这一优化被应用到2016年双11的生产系统里。


Yu Li explains how Alibaba met the challenge of tens of millions requests per second to its Alibaba-Search HBase cluster on 2016 Singles’ Day. Alibaba uses HBase to provide real-time search index updates and as the data store for its online machine learning system. The Alibaba HBase cluster includes 1,500+ nodes and 200,000+ regions, so it’s challenging to maintain a consistent latency and throughput. With read-path off-heaping, Alibaba improved the throughput by 30% and achieved a predicable latency.

Yu Li

Alibaba

Yu Li is a senior technical expert at Alibaba leading the Alibaba Search HBase team. An HBase committer, Yu has over seven years’ work experience in the Hadoop stack for enterprise solution and has supported Alibaba for three Singles’ Days.

Photo of Ramkrishna Vasudevan

Ramkrishna Vasudevan

Intel

Ramkrishna Vasudevan is a senior software engineer at Intel working with Apache HBase. He is also an Apache Phoenix PMC member. Recently, Ramkrishna has been actively working on performance-related features in HBase.

联系OReillyData

关注OReillyData微信号获取最新会议信息并浏览前沿数据文章。

WeChat QRcode

 

Stay Connected Image 1
Stay Connected Image 3
Stay Connected Image 2

阅读关于大数据的最新理念。

ORB Data Site