Wednesday, August 18, 2021

Brian Cooper | PNUTS: Building and Running a Cloud Database System (Dec 11, 2009)

 Aug. 18, 2021

Here is the link. 

Brian Cooper, Research Scientist at Yahoo!, describes PNUTS, a system his team has built at Yahoo! for managing web-scale data. PNUTS is focused on serving systems (low-latency data management to support online web applications) and is complementary to (but different from) our cloud analytical system, Hadoop. Cooper describes the architecture of PNUTS, which has all the (now) standard cloud features of distribution, elastic scalability and failover. He also describes features unique to PNUTS among cloud systems, such as consistency models that go beyond eventual consistency and its worldwide geographic replication. PNUTS is both a research project and a production system, and Cooper describes some of the research we are doing on "next generation" features as well as lessons learned trying to put a research system into production.

Linkedin.com 

Brian Cooper

Principal Software Engineer

Company Name

Google

Dates EmployedJun 2010 – Present

Employment Duration11 yrs 3 mos

I work on Google Apps/Workspace (previously GSuite) infrastructure. Google Apps includes Gmail, Drive, Docs, and other things. I'm the Area Tech Lead for Storage for Apps. In this role I help define the technical strategy for the organization for storage technology, and related areas like reliability and capacity management. I also run a team and that builds and runs several pieces of shared Apps backend infrastructure.

Previously (2012-2017), I work in the storage infrastructure group on the Spanner project. I focused primarily on replication, concurrency control and transaction management, but I also worked on a variety of other aspects of the system. I also managed part of the team.

Before that (2010-2012), I worked on web search. I worked in the ranking group, improving the ranking of results for web queries. This involves analyzing large data sets to extract signals; prototyping ranking changes that use these signals; running experiments to evaluate changes; measuring and tuning the capacity impact of changes; and launching changes into production.

No comments:

Post a Comment