The llama 3 herd of models

A Dubey, A Jauhri, A Pandey, A Kadian… - ar** the performance potential of systems via automatic configuration tuning
Y Zhu, J Liu, M Guo, Y Bao, W Ma, Z Liu… - Proceedings of the …, 2017‏ - dl.acm.org
An ever increasing number of configuration parameters are provided to system users. But
many users have used one configuration setting across different workloads, leaving …

Continuous experimentation: challenges, implementation techniques, and current research

G Schermann, J Cito, P Leitner - Ieee Software, 2018‏ - ieeexplore.ieee.org
Continuous experimentation is an up-and-coming technique for requirements engineering
and testing, particularly for web-based systems. On the basis of a practitioner survey, this …

Xfaas: Hyperscale and low cost serverless functions at meta

A Sahraei, S Demetriou, A Sobhgol, H Zhang… - Proceedings of the 29th …, 2023‏ - dl.acm.org
Function-as-a-Service (FaaS) has become a popular programming paradigm in Serverless
Computing. As the responsibility of resource provisioning shifts from users to cloud …

Canopy: An end-to-end performance tracing and analysis system

J Kaldor, J Mace, M Bejda, E Gao… - Proceedings of the 26th …, 2017‏ - dl.acm.org
This paper presents Canopy, Facebook's end-to-end performance tracing infrastructure.
Canopy records causally related performance data across the end-to-end execution path of …

Early detection of configuration errors to reduce failure damage

T Xu, X **, P Huang, Y Zhou, S Lu, L **… - … USENIX Symposium on …, 2016‏ - usenix.org
Early detection is the key to minimizing failure damage induced by configuration errors,
especially those errors in configurations that control failure handling and fault tolerance …

Twine: A unified cluster management system for shared infrastructure

C Tang, K Yu, K Veeraraghavan, J Kaldor… - … USENIX Symposium on …, 2020‏ - usenix.org
We present Twine, Facebook's cluster management system which has been running in
production for the past decade. Twine has helped convert our infrastructure from a collection …

Advances in using agile and lean processes for software development

P Rodríguez, M Mäntylä, M Oivo, LE Lwakatare… - Advances in …, 2019‏ - Elsevier
Software development processes have evolved according to market needs. Fast changing
conditions that characterize current software markets have favored methods advocating …

{ServiceRouter}: Hyperscale and minimal cost service mesh at meta

H Saokar, S Demetriou, N Magerko… - … USENIX Symposium on …, 2023‏ - usenix.org
Datacenter applications are often structured as many interconnected microservices, and the
service mesh has become a popular approach to route RPC traffic among services. This …