HeROfake: Heterogeneous Resources Orchestration in a Serverless Cloud – An Application to Deepfake Detection - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

HeROfake: Heterogeneous Resources Orchestration in a Serverless Cloud – An Application to Deepfake Detection

Résumé

Serverless is a trending service model for cloud computing. It shifts a lot of the complexity from customers to service providers. However, current serverless platforms mostly consider the provider's infrastructure as homogeneous, as well as the users' requests. This limits possibilities for the provider to leverage heterogeneity in their infrastructure to improve function response time and reduce energy consumption. We propose a heterogeneity-aware serverless orchestrator for private clouds that consists of two components: the autoscaler allocates heterogeneous hardware resources (CPUs, GPUs, FPGAs) for function replicas, while the scheduler maps function executions to these replicas. Our objective is to guarantee function response time, while enabling the provider to reduce resource usage and energy consumption. This work considers a case study for a deepfake detection application relying on CNN inference. We devised a simulation environment that implements our model and a baseline Knative orchestrator, and evaluated both policies with regard to consolidation of tasks, energy consumption and SLA penalties. Experimental results show that our platform yields substantial gains for all those metrics, with an average of 35% less energy consumed for function executions while consolidating tasks on less than 40% of the infrastructure's nodes, and more than 60% less SLA violations.
Fichier principal
Vignette du fichier
HeROfake_Paper.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04165179 , version 1 (18-07-2023)

Licence

Paternité

Identifiants

Citer

Vincent Lannurien, Laurent d'Orazio, Olivier Barais, Esther Bernard, Olivier Weppe, et al.. HeROfake: Heterogeneous Resources Orchestration in a Serverless Cloud – An Application to Deepfake Detection. CCGrid 2023 - IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing, May 2023, Bangalore, India. pp.154-165, ⟨10.1109/CCGrid57682.2023.00024⟩. ⟨hal-04165179⟩
50 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More