Next Article in Journal
Short-Term Analysis of Adhesive Types and Bonding Mistakes on Bonded-in-Rod (BiR) Connections for Timber Structures
Previous Article in Journal
Automatic Extraction of Adverse Drug Reactions from Summary of Product Characteristics
Previous Article in Special Issue
HPC Cloud Architecture to Reduce HPC Workflow Complexity in Containerized Environments
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Enhancing Robustness of Per-Packet Load-Balancing for Fat-Tree

Department of Software & Communications Engineering, Hongik University, Sejong 30016, Korea
Appl. Sci. 2021, 11(6), 2664; https://doi.org/10.3390/app11062664
Submission received: 15 January 2021 / Revised: 6 March 2021 / Accepted: 15 March 2021 / Published: 17 March 2021
(This article belongs to the Special Issue High-Performance Computing and Supercomputing)

Abstract

Fat-tree networks have many equal-cost redundant paths between two hosts. To achieve low flow completion time and high network utilization in fat-tree, there have been many efforts to exploit topological symmetry. For example, packet scatter schemes, which spray packets across all equal-cost paths relying on topological symmetry, work well when there is no failure in networks. However, when symmetry of a network is disturbed due to a network failure, packet scatter schemes may suffer massive packet reordering. In this paper, we propose a new load balancing scheme named LBSP (Load Balancing based on Symmetric Path groups) for fat-trees. LBSP partitions equal-cost paths into equal sized path groups and assigns a path group to each flow so that packets of a flow are forwarded across paths within the selected path group. When a link failure occurs, the flows affected by the failure are assigned an alternative path group which does not contain the failed link. Consequently, packets in one flow can still experience almost the same queueing delay. Simulation results show that LBSP is more robust to network failures compared to the original packet scatter scheme. We also suggest a solution to the queue length differentials between path groups.
Keywords: fat-tree; per-packet load-balancing; packet-reordering fat-tree; per-packet load-balancing; packet-reordering

Share and Cite

MDPI and ACS Style

Lim, C. Enhancing Robustness of Per-Packet Load-Balancing for Fat-Tree. Appl. Sci. 2021, 11, 2664. https://doi.org/10.3390/app11062664

AMA Style

Lim C. Enhancing Robustness of Per-Packet Load-Balancing for Fat-Tree. Applied Sciences. 2021; 11(6):2664. https://doi.org/10.3390/app11062664

Chicago/Turabian Style

Lim, Chansook. 2021. "Enhancing Robustness of Per-Packet Load-Balancing for Fat-Tree" Applied Sciences 11, no. 6: 2664. https://doi.org/10.3390/app11062664

APA Style

Lim, C. (2021). Enhancing Robustness of Per-Packet Load-Balancing for Fat-Tree. Applied Sciences, 11(6), 2664. https://doi.org/10.3390/app11062664

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop