Back to Search Start Over

Mesa

Authors :
Jeff Shute
Fan Yang
Divyakant Agrawal
Andrey Gubarev
Sanjay Bhansali
Ankur Agiwal
Abhilash Rajesh Kumar
Shuo Wu
Kelvin K. W. Chan
Kevin Lai
Sandeep Govind Dhoot
Shivakumar Venkataraman
Adam Kirsch
Ashish Gupta
Mingsheng Hong
Masood Siddiqi
David Jones
Jason Govig
Jamie Cameron
Source :
Communications of the ACM. 59:117-125
Publication Year :
2016
Publisher :
Association for Computing Machinery (ACM), 2016.

Abstract

Mesa is a highly scalable analytic data warehousing system that stores critical measurement data related to Google's Internet advertising business. Mesa is designed to satisfy a complex and challenging set of user and systems requirements, including near real-time data ingestion and retrieval, as well as high availability, reliability, fault tolerance, and scalability for large data and query volumes. Specifically, Mesa handles petabytes of data, processes millions of row updates per second, and serves billions of queries that fetch trillions of rows per day. Mesa is geo-replicated across multiple datacenters and provides consistent and repeatable query answers at low latency, even when an entire datacenter fails. This paper presents the Mesa system and reports the performance and scale that it achieves.

Details

ISSN :
15577317 and 00010782
Volume :
59
Database :
OpenAIRE
Journal :
Communications of the ACM
Accession number :
edsair.doi...........5a2ff63ba904fc5f5c393aed74111446
Full Text :
https://doi.org/10.1145/2936722