TL;DR
This thesis argues that database systems can support expressive workloads without sacrificing performance or correctness by recovering and propagating this information across system boundaries.
Relational data stores are widely used because they provide persistence, scalability, and fault tolerance with a simple interface. However, most data store applications configure the data store to use weak isolation for scalable performance, permitting sporadic unserializable executions that produce incorrect results o...
Modern web applications are increasingly reliant on Object-Relational Mapper (ORM) frameworks to bridge the gap between high-level application logic and relational databases. However, in standard Create, Read, Update, and Delete (CRUD) architectures, the use of a unified data model often leads to significant performanc...
This paper introduces Controlled Pushdown Execution (CPE), a white-box method that enables systematic validation of computation pushdown and shows that CPE can control all supported operators across different systems.
An extension to the compilation process with a post-verification optimization phase to address the eBPF verifier limitation and measure the performance overhead introduced by these restrictions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
