Cheetah: Accelerating Database Queries with Switch Pruning

TL;DR

Cheetah leverages programmable switches to perform data pruning, reducing query processing time in distributed databases by offloading filtering tasks to network hardware, achieving significant speedups.

Contribution

This paper introduces data pruning algorithms for switch-based query offloading, enabling efficient query acceleration within switch resource constraints.

Findings

Achieves 40-200% reduction in query completion time

Successfully implements pruning algorithms on Barefoot Tofino switches

Demonstrates significant performance improvements across multiple workloads

Abstract

Modern database systems are growing increasingly distributed and struggle to reduce query completion time with a large volume of data. In this paper, we leverage programmable switches in the network to partially offload query computation to the switch. While switches provide high performance, they have resource and programming constraints that make implementing diverse queries difficult. To fit in these constraints, we introduce the concept of data \emph{pruning} -- filtering out entries that are guaranteed not to affect output. The database system then runs the same query but on the pruned data, which significantly reduces processing time. We propose pruning algorithms for a variety of queries. We implement our system, Cheetah, on a Barefoot Tofino switch and Spark. Our evaluation on multiple workloads shows $40 - 200\%$ improvement in the query completion time compared to Spark.