ScaleReactor: A graceful performance isolation agent with interference detection and investigation for container‐based scale‐out workloads

2021 ◽  
Author(s):  
Jianyong Zhu ◽  
Chunming Hu ◽  
Tianyu Wo ◽  
Xiaoqiang Yu
Keyword(s):  
Interference Detection ◽  
Performance Isolation

Versatile and Configurable GNSS Interference Detection and Characterization Station

2017 ◽  
Author(s):  
Alexander R�gamer ◽  
Daniel Meister ◽  
J. Rossouw van der Merwe ◽  
Christian Otto ◽  
Manuel Stahl ◽  
...  
Keyword(s):  
Interference Detection

scholarly journals QiOi: Performance Isolation for Hyperledger Fabric

2021 ◽  
Vol 11 (9) ◽  
pp. 3870
Author(s):  
Jeongsu Kim ◽  
Kyungwoon Lee ◽  
Gyeongsik Yang ◽  
Kwanhoon Lee ◽  
Jaemin Im ◽  
...  
Keyword(s):  
Data Centers ◽  
Component Level ◽  
Isolation Technique ◽  
Cloud Data ◽  
Cpu Scheduling ◽  
Performance Isolation ◽  
Cloud Data Centers ◽  
A New Technique ◽  
The Impact ◽  
Level Performance

This paper investigates the performance interference of blockchain services that run on cloud data centers. As the data centers offer shared computing resources to multiple services, the blockchain services can experience performance interference due to the co-located services. We explore the impact of the interference on Fabric performance and develop a new technique to offer performance isolation for Hyperledger Fabric, the most popular blockchain platform. First, we analyze the characteristics of the different components in Hyperledger Fabric and show that Fabric components have different impacts on the performance of Fabric. Then, we present QiOi, component-level performance isolation technique for Hyperledger Fabric. The key idea of QiOi is to dynamically control the CPU scheduling of Fabric components to cope with the performance interference. We implement QiOi as a user-level daemon and evaluate how QiOi mitigates the performance interference of Fabric. The evaluation results demonstrate that QiOi mitigates performance degradation of Fabric by 22% and improves Fabric latency by 2.5 times without sacrificing the performance of co-located services. In addition, we show that QiOi can support different ordering services and chaincodes with negligible overhead to Fabric performance.

Sign in / Sign up

Export Citation Format

Share Document