FAMD: A Flow-Aware Marking and Delay-based TCP algorithm for datacenter networks

Abstract Datacenter networks have brought new challenges to meet datacenters’ unique performance requirements. Moreover, the many-to-one traffic pattern, which is quite common in datacenter networks, causes heavy network congestion and leads to TCP incast problem. To solve this problem, many TCP congestion control protocols have been proposed to mitigate the TCP incast. However, these protocols have more or less problems, including high computational complexity and implementation complexity. In this paper, we propose a flow-aware marking and delay-based TCP algorithm for datacenters, referred to as FAMD. FAMD is built on the delay-based protocols and leverages a DCTCP-like marking scheme to indicate the network congestion level and regulate the congestion window. Based on above mechanism, FAMD can maintain a low and stable transmission end-to-end delay. Furthermore, because of the disadvantage of fixed marking threshold, this paper shows how to choose an appropriate threshold dynamically and presents a flow-aware threshold adjustment algorithm, referred to FATA. Therefore, our FAMD can achieve a good generality for different scenarios. Our extensive evaluation shows that FAMD can gain a good throughput and low end-to-end delay.

[1]  Haitao Wu,et al.  ICTCP: Incast Congestion Control for TCP in Data-Center Networks , 2010, IEEE/ACM Transactions on Networking.

[2]  Larry L. Peterson,et al.  TCP Vegas: End to End Congestion Avoidance on a Global Internet , 1995, IEEE J. Sel. Areas Commun..

[3]  Yifei Lu,et al.  SED: An SDN-Based Explicit-Deadline-Aware TCP for Cloud Data Center Networks , 2016 .

[4]  Jae-Hyun Hwang,et al.  Deadline and Incast Aware TCP for cloud data center networks , 2014, Comput. Networks.

[5]  Ming Zhang,et al.  Understanding data center traffic characteristics , 2010, CCRV.

[6]  Changhyun Lee,et al.  DX: Latency-Based Congestion Control for Datacenters , 2017, IEEE/ACM Transactions on Networking.

[7]  Amin Vahdat,et al.  TIMELY: RTT-based Congestion Control for the Datacenter , 2015, Comput. Commun. Rev..

[8]  Ling Tang,et al.  SDTCP: Towards Datacenter TCP Congestion Control with SDN for IoT Applications , 2017, Sensors.

[9]  Brahim Bensaou,et al.  Curbing Timeouts for TCP-Incast in Data Centers via A Cross-Layer Faster Recovery Mechanism , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[10]  Guihai Chen,et al.  DC-ECN: A machine-learning based dynamic threshold control scheme for ECN marking in DCN , 2020, Comput. Commun..

[11]  Van Jacobson,et al.  BBR: Congestion-Based Congestion Control , 2016, ACM Queue.

[12]  Tao Yang,et al.  The Panasas ActiveScale Storage Cluster - Delivering Scalable High Bandwidth Storage , 2004, Proceedings of the ACM/IEEE SC2004 Conference.

[13]  Hong Liu,et al.  Jupiter Rising: A Decade of Clos Topologies and Centralized Control in Google's Datacenter Network , 2015, Comput. Commun. Rev..

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

[15]  Hamed Rezaei,et al.  ICON: Incast Congestion Control using Packet Pacing in Datacenter Networks , 2019, 2019 11th International Conference on Communication Systems & Networks (COMSNETS).

[16]  Zhenhua Liu,et al.  HUG: Multi-Resource Fairness for Correlated and Elastic Demands , 2016, NSDI.

[17]  Brahim Bensaou,et al.  Hysteresis-based Active Queue Management for TCP Traffic in Data Centers , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[18]  Dimitrios P. Pezaros,et al.  Measurement-based TCP parameter tuning in cloud data centers , 2013, 2013 21st IEEE International Conference on Network Protocols (ICNP).

[19]  Gautam Kumar,et al.  Swift: Delay is Simple and Effective for Congestion Control in the Datacenter , 2020, SIGCOMM.

[20]  Yan Li,et al.  TS-TCP: Two-Stage Congestion Control Algorithm for High Concurrency TCPs in Data Center Networks , 2019, 2019 28th International Conference on Computer Communication and Networks (ICCCN).

[21]  T. N. Vijaykumar,et al.  Deadline-aware datacenter tcp (D2TCP) , 2012, SIGCOMM '12.

[22]  Chao Li,et al.  DC-Vegas: A delay-based TCP congestion control algorithm for datacenter applications , 2015, J. Netw. Comput. Appl..

[23]  Fengyuan Ren,et al.  Micro-Burst in Data Centers: Observations, Analysis, and Mitigations , 2018, 2018 IEEE 26th International Conference on Network Protocols (ICNP).

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

[25]  Chuang Lin,et al.  Sharing Bandwidth by Allocating Switch Buffer in Data Center Networks , 2014, IEEE Journal on Selected Areas in Communications.

[26]  Raj Jain,et al.  A Quantitative Measure Of Fairness And Discrimination For Resource Allocation In Shared Computer Systems , 1998, ArXiv.

[27]  PadhyeJitendra,et al.  Data center TCP (DCTCP) , 2010 .

[28]  Shuo Wang,et al.  A-ECN Minimizing Queue Length for Datacenter Networks , 2020, IEEE Access.

[29]  Jianxin Wang,et al.  ARS: Cross-layer adaptive request scheduling to mitigate TCP incast in data center networks , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[30]  Yifei Lu,et al.  Dynamic ECN marking threshold algorithm for TCP congestion control in data center networks , 2018, Comput. Commun..

[31]  Guihai Chen,et al.  ECN+: A marking-aware optimization for ECN threshold via per-Port in Data Center Networks , 2020, J. Netw. Comput. Appl..

[32]  Hari Balakrishnan,et al.  Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control , 2018, ANRW.

[33]  Mike Nilsson,et al.  TCP Congestion Response for Low Latency HTTP Live Streaming , 2018, 2018 IEEE 19th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).