Abstract

Today, datacenter operators deploy Load-balancers (LBs) to efficiently utilize server resources, but must over-provision server resources (by up to 30%) because of load imbalances and the desire to bound tail service latency. We posit one of the reasons for these imbalances is the lack of per-core load statistics in existing LBs. As a first step, we designed CrossRSS, a CPU core-aware LB that dynamically assigns incoming connections to the least loaded cores in the server pool. CrossRSS leverages knowledge of the dispatching by each server's Network Interface Card (NIC) to specific cores to reduce imbalances by more than an order of magnitude compared to existing LBs in a proof-of-concept datacenter environment, processing 12% more packets with the same number of cores.

Keywords:
Computer science Stateless protocol Server Load balancing (electrical power) Computer network Network packet Latency (audio) Operating system Core (optical fiber) Distributed computing

Metrics

7
Cited By
0.68
FWCI (Field Weighted Citation Impact)
7
Refs
0.72
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Software-Defined Networks and 5G
Physical Sciences →  Computer Science →  Computer Networks and Communications
Cloud Computing and Resource Management
Physical Sciences →  Computer Science →  Information Systems
Interconnection Networks and Systems
Physical Sciences →  Computer Science →  Computer Networks and Communications
© 2026 ScienceGate Book Chapters — All rights reserved.