OTCP: SDN-managed congestion control for data center networks

TCP suffers from incast collapse in data center networks when used with partition aggregate workloads due to inadequate congestion control parameters. This causes poor application performance by under-utilizing the network, and can be one of the limiting factors in low-latency, high-throughput environments. To resolve this, we present Omniscient TCP (OTCP), a Software Defined Networking (SDN) approach to compute environment-specific congestion control parameters based on centrally available network properties. Through experimental evaluation in Mininet, we show up to 12x and 31x reduction in Flow Completion Time (FCT) at the mean and 95th percentile, an 8x FCT improvement on highly congested networks when combined with DCTCP [1], as well as improved fairness and reduced end-to-end latency.

[1]  Luiz André Barroso,et al.  The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines , 2009, The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines.

[2]  Aditya Akella,et al.  Understanding data center traffic characteristics , 2009, WREN 2009.

[3]  David A. Maltz,et al.  Network traffic characteristics of data centers in the wild , 2010, IMC '10.

[4]  Devavrat Shah,et al.  Fastpass: a centralized "zero-queue" datacenter network , 2015, SIGCOMM 2015.

[5]  Dimitrios P. Pezaros,et al.  Arbitrary packet matching in OpenFlow , 2015, 2015 IEEE 16th International Conference on High Performance Switching and Routing (HPSR).

[6]  Amar Phanishayee,et al.  Safe and effective fine-grained TCP retransmissions for datacenter communication , 2009, SIGCOMM '09.

[7]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[8]  Hari Balakrishnan,et al.  TCP ex machina: computer-generated congestion control , 2013, SIGCOMM.

[9]  Y. Zhang,et al.  An implementation and experimental study of the explicit control protocol (XCP) , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[10]  Amin Vahdat,et al.  Hedera: Dynamic Flow Scheduling for Data Center Networks , 2010, NSDI.

[11]  IEEE/IFIP Network Operations and Management Symposium, NOMS 2010, 19-23 April 2010, Osaka, Japan , 2010, IEEE/IFIP Network Operations and Management Symposium.

[12]  Carey L. Williamson,et al.  Solving the TCP-Incast Problem with Application-Level Scheduling , 2012, 2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems.

[13]  Albert G. Greenberg,et al.  The cost of a cloud: research problems in data center networks , 2008, CCRV.

[14]  George Varghese,et al.  P4: programming protocol-independent packet processors , 2013, CCRV.

[15]  Rob Sherwood,et al.  OFLOPS: An Open Framework for OpenFlow Switch Evaluation , 2012, PAM.

[16]  Cheng Jin,et al.  FAST TCP: Motivation, Architecture, Algorithms, Performance , 2006, IEEE/ACM Transactions on Networking.

[17]  Nick McKeown,et al.  Why flow-completion time is the right metric for congestion control , 2006, CCRV.

[18]  Srinivasan Seshan,et al.  Measurement and Analysis of TCP Throughput Collapse in Cluster-based Storage Systems , 2008, FAST.

[19]  Li Tang,et al.  Taming TCP incast throughput collapse in data center networks , 2013, 2013 21st IEEE International Conference on Network Protocols (ICNP).

[20]  Junda Liu,et al.  Multi-enterprise networking , 2000 .

[21]  Mo Dong,et al.  PCC: Re-architecting Congestion Control for Consistent High Performance , 2014, NSDI.

[22]  Stuart Cheshire.  IPv4 Address Conflict Detection , 2008, RFC.

[23]  David A. Maltz,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM 2010.