EdgeIso: Effective Performance Isolation for Edge Devices

  • Nam, Yoonsung; 
  • Choi, Yongjun; 
  • Yoo, Byeonghun; 
  • Eom, Hyeonsang; 
  • Son, Yongseok
Citations

WEB OF SCIENCE

6
Citations

SCOPUS

7

초록

Edges enable cloud services to be provided at low-latency and efficiently reduce the amount of transferred data by placing latency-critical tasks close to users. However, multi-tasking results in resource contention on edge devices, making it challenging to meet the service level objectives (SLOs) of tasks. Compared to the clouds, edges have relatively limited resources, but their tasks are required to meet a higher level of SLOs than clouds. Furthermore, modern edge devices equipped with additional accelerators (e.g., GPU) may worsen the resource contention due to the edge's integrated architecture, sharing the memory bandwidth between CPUs and accelerators. To address these challenges, we present EdgeIso, a light-weight scheduler that dynamically isolates the performance of tasks on edges. EdgeIso periodically monitors the resource contention and mitigates the contention to meet the SLOs of tasks by efficiently enforcing several isolation techniques (e.g., DVFS and core allocation) in an incremental manner. Moreover, it detects the changes of task executions or offered loads for tasks, thus handling high load fluctuations adaptively. We implement EdgeIso as a user-level scheduler on the Linux integrates into an NVIDIA Jetson TX2. Our experimental results show that EdgeIso improves the performance of the low-latency tasks significantly while improving resource efficiency compared with both the offloading and reservation scheme used in clouds.

키워드

edge computing; resource management; performance isolation; latency-critical workloads
제목
EdgeIso: Effective Performance Isolation for Edge Devices
저자
Nam, Yoonsung; Choi, Yongjun; Yoo, Byeonghun; Eom, Hyeonsang; Son, Yongseok
DOI
10.1109/IPDPS47924.2020.00039
발행일
2020-05
유형
Proceedings Paper
저널명
2020 IEEE 34TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM IPDPS 2020
페이지
295 ~ 305