Fast core scheduling with userspace process abstraction

J Lin, Y Chen, S Gao, Y Lu - Proceedings of the ACM SIGOPS 30th …, 2024 - dl.acm.org
We introduce uProcess, a pure userspace process abstraction that enables CPU cores to be
rescheduled among applications at sub-microsecond timescale without trapping into the …

Junctiond: Extending FaaS Runtimes with Kernel-Bypass

E Saurez, J Fried, GI Chaudhry, E Choukse… - arXiv preprint arXiv …, 2024 - arxiv.org
This report explores the use of kernel-bypass networking in FaaS runtimes and
demonstrates how using Junction, a novel kernel-bypass system, as the backend for …

Can OS Specialization give new life to old carbon in the cloud?

H Dong, S Arora, O Krieger, J Appavoo - Proceedings of the 17th ACM …, 2024 - dl.acm.org
Is there" fat"(overheads) in cloud computing infrastructure software that can be trimmed?
Would doing so help ameliorate the need for frequent hardware refreshes and extend the …

[PDF][PDF] Can we optimize without specializing?

A Panda - apanda.me
The systems research community spends a lot of its time optimizing systems to improve their
performance and reduce resource requirements [6, 7, 13, 14, 16, 17, 20, 21]. We justify this …

[PDF][PDF] Hermes: Evaluating Enso Schedulers for High-Performance Networking

K Gupta - 2024 - reports-archive.adm.cs.cmu.edu
Kernel bypass has recently gained popularity as a way to achieve high-performance
networking. However, it pays for its improvements in performance with CPU efficiency. For …

[PDF][PDF] Shared Memory Pool for Representors

W Tu, M Swiatkowski, Y Kuperman - netdevconf.info
Representor is a special object that controls the slow path of switchdev virtual port, or vport
(the representee). When scaling to thousands of vports, a corresponding thousands of …