Loading [MathJax]/extensions/MathZoom.js
OS4C: An Open-Source SR-IOV System for SmartNIC-Based Cloud Platforms | IEEE Conference Publication | IEEE Xplore

OS4C: An Open-Source SR-IOV System for SmartNIC-Based Cloud Platforms


Abstract:

Smart network interface cards (SmartNICs) are programmable network cards that enable the flexible offloading of network- and application-level functionality. The last sev...Show More

Abstract:

Smart network interface cards (SmartNICs) are programmable network cards that enable the flexible offloading of network- and application-level functionality. The last several years have seen a significant rise in research related to smart, programmable NICs. Meanwhile, several open-source FPGA-based NIC and networking projects have emerged. However, these projects lack many key features necessary for strong performance in cloud settings. We identify Single Root In-put/Output Virtualization (SR-IOV) as one of the key missing features in these open-source implementations. SR-IOV enables cloud vendors to grant cloud tenants direct access to hardware resources, dramatically reducing the software overheads of device virtualization. We present OS4C, which extends the popular open-source NIC Corundum [1] with support for SR-IOV. We demonstrate that OS4C can improve virtual machine P99.9 network tail latency by up to 17x, throughput by up to 4x, and CPU effort by up to 3.9x compared to software virtualization. On top of this system, we provide a novel weighted round-robin scheduler that enables tenants and providers to control weight distributions and overhaul the Corundum simulation framework to support multi-tenant tests and performance insights.
Date of Conference: 07-13 July 2024
Date Added to IEEE Xplore: 28 August 2024
ISBN Information:

ISSN Information:

Conference Location: Shenzhen, China
No metrics found for this document.

I. Introduction

Over a decade ago, researchers noticed a growing gap between server CPU performance and network throughput demands. This drove them to explore how to make CPU networking tasks more efficient. For example, MegaPipe [2] proposed a novel network stack that reduced operating system overheads. This gap has not disappeared; it has become even more pronounced due to increasing link speeds that have grown faster than single-core CPU performance [3]. Many researchers and companies have developed novel hardware and software features to improve network performance to try and combat this increasing gap [2], [4]–[7].

Usage
Select a Year
2025

View as

Total usage sinceSep 2024:221
01020304050JanFebMarAprMayJunJulAugSepOctNovDec41340000000000
Year Total:75
Data is updated monthly. Usage includes PDF downloads and HTML views.
Contact IEEE to Subscribe

References

References is not available for this document.