Choosing between Efficiency and Performance with RocksDB
Choosing between Efficiency and Performance with RocksDB
RocksDB supports many tradeoffs between read, write and space efficiency. While more choices implies more complexity in tuning the end result can be worth the effort. I will explain how this is possible in RocksDB and why it motivated migrating a large MySQL tier from InnoDB to the RocksDB storage engine for MySQL named MyRocks.
Talk objectives:
- Explain read, write and space efficiency for databases in theory and practice.
Target audience:
- People who care about database efficiency.
About Mark
Mark worked with great teams to make MySQL better for web-scale deployments at Facebook & Google for more than 11 years. He now works at Facebook on RocksDB, MyRocks and MongoDB with a focus on storage efficiency. Prior to his web-scale career he spent many years working on RDBMS internals at Oracle and Informix. He invented and implemented a fast sort algorithm for the Oracle RDBMS. He has an MS in CS from UW-Madison.
Github: mdcallag
Twitter: @markcallaghan