Offloading Data Center Tax

TL;DR

This paper investigates offloading multiple tax components in data center workloads, specifically focusing on MongoDB within the DeathStarBench suite, to improve performance through microarchitectural analysis and targeted offloading strategies.

Contribution

It identifies opportunities for offloading multiple tax components in MongoDB, providing insights into their microarchitectural implications and suggesting potential performance improvements.

Findings

Identified tax components in MongoDB with microarchitectural impact

Proposed strategies for offloading multiple tax components together

Demonstrated potential performance gains through targeted offloading

Abstract

The data centers of today are running diverse workloads sharing many common lower level functions called tax components. Any optimization to any tax component will lead to performance improvements across the data center fleet. Typically, performance enhancements in tax components are achieved by offloading them to accelerators, however, it is not practical to offload every tax component. The goal of this paper is to identify opportunities to offload more than one tax component together. We focus on MongoDB which is a common microservice used in a large number of applications in the datacenter. We profile MongoDB running as part of the DeathStarBench benchmark suite, identifying its tax components and their microarchitectural implications. We make observations and suggestions based on the inferences made to offload a few of the tax components in this application.