NoisePage is an in-memory relational DBMS designed to support self-driving (i.e., autonomous) operation. It is developed by the Carnegie Mellon Database Group.
- Website
- https://noise.page[01]
- Source Code
- https://github.com/cmu-db/noisepage[02]
- @NoisePageDB
- Developer
- Country of Origin
- US
- Start Year
- 2018
- Former Name
- Peloton
- Project Types
- Academic, Open Source
- Written in
- C++
- Inspired By
- HyPer
- Compatible With
- PostgreSQL
- License
- MIT License
NoisePage is an in-memory relational DBMS designed to support self-driving (i.e., autonomous) operation. It is developed by the Carnegie Mellon Database Group.
History
The CMU Database Group abandoned the Peloton project in 2018 and started building NoisePage from scratch.
Indexes[05]
NoisePage started with the Bw-Tree index from the Peloton project. In 2021, the Bw-Tree was replaced by a B+Tree as the default index data structure.
Query Compilation[06]
NoisePage transforms query plans into a database-centric DSL called TPL ("terrier programming language"). The DBMS then compiles the TPL program into bytecodes that it can either interpret with its own VM or compile into machine code with LLVM.
Citations
6 sources- https://noise.page noise.page
- https://github.com/cmu-db/noisepage github.com
- noisepage/docs at master · cmu-db/noisepage · GitHub github.com
- Mainlining Databases: Supporting Fast Transactional Workloads on Universal Columnar Data File Formats cmu.edu
- Concurrent B+ Tree (#1383) Co-authored-by: Matt Butrovich <[email protected]> Co-authored-by: Rohan Aggarwal <[email protected]> Co-authored-by: gautam20197 <[email protected]> Co-authore github.com
- Permutable Compiled Queries: Dynamically Adapting Compiled Queries without Recompiling cmu.edu