ABSTRACT
In this paper, we aim to effectively utilize in-network buffering to schedule and route packets with low communication overhead, small delay and throughput optimality in fat-tree networks. While nearly zero in-network queueing can be guaranteed by performing precise time allocation and path assignment at network endpoints as in Fastpass, there is a high communication overhead, and buffer occupancy at the endpoints can become bottlenecks. By spreading scheduling functionalities to different network layers in a fat-tree network, the complexity can be decreased significantly at the cost of moderate buffer occupancy at intermediate switches. Inspired by this observation, we propose a simple dynamic pod scheduling (DPS) scheme, which performs scheduling at the granularity of pod units, each of which is paired to at most one other pod unit to transmit packets at each slot. By doing so, less information is required to arrange the packet transfers and inter-pod traffic will experience less downlink contentions. Through extensive evaluations, we find that DPS outperforms Fastpass in terms of delay while still guaranteeing throughput-optimality.
- G. Wang, D. G. Andersen, M. Kaminsky, et. al., "c-Through: Part-time Optics in Data Centers," in Proc. SIGCOMM, 2010. Google ScholarDigital Library
- M. Alizadeh, S. Yang, M. Sharif, et. al., "pFabric: Minimal Near-Optimal Datacenter Transport," in Proc. SIGCOMM, 2013. Google ScholarDigital Library
- C.-H. Wang and T. Javidi, "Adaptive Policies for Scheduling with Reconfiguration Delay: An End-to-End Solution for All-Optical Data Centers," IEEE/ACM Transactions on Networking, vol. 25, no. 3, Jun. 2017. Google ScholarDigital Library
- J. Perry, A. Ousterhout, A. Ousterhout, et. al., "Fastpass: A Centralized "Zero-Queue" Datacenter Network," in Proc. SIGCOMM, 2014. Google ScholarDigital Library
- N. McKeown, A. Mekkittikul, V. Anantharam, et. al., "Achieving 100% Throughput in an Input-Queued Switch," IEEE Transactions on Communications, vol. 47, no. 8, pp. 1260--1267, 1999.Google ScholarCross Ref
- M. Al-Fares, A. Loukissas and A. Vahdat, "A Scalable, Commodity Data Center Network Architecture," in Proc. SIGCOMM, 2008. Google ScholarDigital Library
- Utilizing In-Network Buffering for Scheduling and Routing in Data Center Networks
Recommendations
Efficient buffering techniques for deflection routing in high speed networks
LCN '96: Proceedings of the 21st Annual IEEE Conference on Local Computer NetworksDeflection routing is a simple, decentralized, and adaptive routing methodology for communication networks. We focus on deflection routing in the Benes network. Since deflection routing forces packets to take multiple paths to the destination, packets ...
A packet forwarding controller for mobile IP-based networks with packet buffering
Performance of TCP can be severely degraded in Mobile IP-based wireless networks where packet losses not related to network congestion occur frequently during inter-subnetwork handoffs by user mobility. To solve such a problem in the networks using ...
Performance study of buffering within switches in local area networks
ICCCN '95: Proceedings of the 4th International Conference on Computer Communications and NetworksAbstract: Today's demanding applications, such as multimedia, require higher network transfer rates. Traditional local area networks (LANs) will not be able to provide the throughput required by these applications. The use of switches in LANs is an ...
Comments