User-Level Network Programmability: A Scalability Study for Data Center Infrastructure

This paper evaluates the scalability of user-level network programmability in data centers, focusing on the performance of applications developed using the Data Plane Development Kit (DPDK). DPDK is a high-performance framework for fast packet processing in user space, bypassing traditional kernel-based network stacks. Results show DPDK's potential to maintain high packet transfer rates while optimizing CPU and memory usage under varying packet sizes and processing demands. However, the performance is significantly impacted by hardware limitations, such as memory channels and network interface controllers (NICs). The findings emphasize DPDK's scalability, especially in cloud data centers, where modern applications require low-latency and high-throughput networking solutions.

Authors

Institutions

Publication Details

Published
2024-11-13
DOI
https://doi.org/10.1109/sbac-padw64858.2024.00017
Primary Topic
Cloud Computing and Resource Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

User-Level Network Programmability: A Scalability Study for Data Center Infrastructure

Bryan C. Souza, Paulo Sergio de Souza, Marcelo Caggiani Luizelli, Patric Lincoln Ramires Izolan et al.
Cloud Computing and Resource Management
article

User-Level Network Programmability: A Scalability Study for Data Center Infrastructure

Bryan C. Souza, Paulo Sergio de Souza, Marcelo Caggiani Luizelli, Patric Lincoln Ramires Izolan, Isaias Miranda Júnior, Fábio Diniz Rossi, Angelo V. Crestani, Ester S. Oribes
article en

Abstract

This paper evaluates the scalability of user-level network programmability in data centers, focusing on the performance of applications developed using the Data Plane Development Kit (DPDK). DPDK is a high-performance framework for fast packet processing in user space, bypassing traditional kernel-based network stacks. Results show DPDK's potential to maintain high packet transfer rates while optimizing CPU and memory usage under varying packet sizes and processing demands. However, the performance is significantly impacted by hardware limitations, such as memory channels and network interface controllers (NICs). The findings emphasize DPDK's scalability, especially in cloud data centers, where modern applications require low-latency and high-throughput networking solutions.

Instituto Federal Farroupilha (BR), Universidade Federal do Pampa (BR)
Industry, innovation and infrastructure
Openalex Percentile: Top 67%
Cloud Computing and Resource Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.