RDMA Performance Isolation With Justitia

05/11/2019
by   Yiwen Zhang, et al.
0

Despite its increasing popularity, most of RDMA's benefits such as ultra-low latency can be achieved only when running an application in isolation. Using microbenchmarks and real open-source RDMA applications, we identify a series of performance anomalies when multiple applications coexist and show that such anomalies are pervasive across InfiniBand, RoCEv2, and iWARP. They arise due to a fundamental tradeoff between performance isolation and work conservation, which the state-of-the-art RDMA congestion control protocols such as DCQCN cannot resolve. We present Justitia to address these performance anomalies. Justitia is a software-only, host-based, and easy-to-deploy solution that maximizes RNIC utilization while guaranteeing performance isolation via shaping, rate limiting, and pacing at senders. Our evaluation of Justitia on multiple RDMA implementations show that Justitia effectively isolates different types of traffic and significantly improves latency (by up to 56.9x) and throughput (by up to 9.7x) of real-world RDMA-based applications without compromising low CPU usage or modifying the applications.

READ FULL TEXT

page 10

page 11

research
10/27/2021

Systematic definition and classification of data anomalies in DBMS (English Version)

There is no unified definition of Data anomalies, which refers to the sp...
research
10/08/2020

5G Network Slice Isolation with WireGuard and Open Source MANO: A VPNaaS Proof-of-Concept

The fifth-generation (5G) mobile networks aim to host different types of...
research
09/14/2021

Coo: Rethink Data Anomalies In Databases

Transaction processing technology has three important contents: data ano...
research
04/22/2023

Collie: Finding Performance Anomalies in RDMA Subsystems

High-speed RDMA networks are getting rapidly adopted in the industry for...
research
11/24/2018

TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep LearningInference in Function as a Service Environments

Deep neural networks (DNNs) have become core computation components with...
research
01/27/2020

Identifying Requirements Affecting Latency in a Softwarized Network for Future 5G and Beyond

The concept of a softwarized network leveraging technologies such as SDN...
research
02/22/2021

Reading from External Memory

Modern external memory is represented by several device classes. At pres...

Please sign up or login with your details

Forgot password? Click here to reset