PPT: A Pragmatic Transport for Datacenters
Authors: 
Lide Suo, Yiren Pang, Wenxin Li, Renjie Pei, Keqiu Li, Xiulong Liu, Xin He, Yitao Hu, Guyue LiuAuthors Info & Claims
Lide Suo, Yiren Pang, Wenxin Li, Renjie Pei, Keqiu Li, Xiulong Liu, Xin He, Yitao Hu, Guyue LiuAuthors Info & ClaimsPages 954 - 969
Abstract
This paper introduces PPT, a pragmatic transport that achieves comparable performance to proactive transports while maintaining good deployability as reactive transports. Our key idea is to run a low-priority control loop to leverage the available bandwidth left by the reactive transports. The main challenge is to send just enough packets to improve performance without harming the primary control loop. We combine two unconventional techniques: an intermittent loop initialization and an exponential window decrease, enabling us to dynamically identify and fill the spare bandwidth. We further complement PPT's design with a buffer-aware flow scheduling scheme to optimize the average FCT of small flows without prior knowledge of flow size information. We have implemented a PPT prototype in the Linux kernel with ~400 lines of code and demonstrated that compared to Homa, it delivers up to 46.3% lower overall average FCT and even 25%/55.5% lower average/tail FCT of small flows in an Memcached workload.
References
[1]
ACID: Distributed Service Governance Framework. https://github.com/zavier-wong/acid.
[2]
DCTCP in Linux Kernel 3.18, 2014. https://kernelnewbies.org/Linux_3.18.
[3]
DCTCP in Windows Server, 2012. http://technet.microsoft.com/en-us/library/hh997028.aspx.
[4]
Memcached. http://memcached.org/.
[5]
Alizadeh, M., Greenberg, A., Maltz, D. A., Padhye, J., Patel, P., Prabhakar, B., Sengupta, S., and Sridharan, M. Data center tcp (dctcp). In SIGCOMM (2010).
[6]
Alizadeh, M., Kabbani, A., Edsall, T., Prabhakar, B., Vahdat, A., and Yasuda, M. Less Is More: Trading a Little Bandwidth for Ultra-Low Latency in the Data Center. In NSDI (2012).
[7]
Alizadeh, M., Yang, S., Sharif, M., Katti, S., McKeown, N., Prabhakar, B., and Shenker, S. pfabric: Minimal near-optimal datacenter transport. In SIGCOMM (2013).
[8]
Atikoglu, B., Xu, Y., Frachtenberg, E., Jiang, S., and Paleczny, M. Workload analysis of a large-scale key-value store. In Proceedings of ACM SIGMETRICS (2012).
[9]
Bai, W., Chen, L., Chen, K., Han, D., Tian, C., and Wang, H. Information-Agnostic Flow Scheduling for Commodity Data Centers. In NSDI (2015).
[10]
Bai, W., Hu, S., Chen, K., Tan, K., and Xiong, Y. One more config is enough: Saving (DC) TCP for high-speed extremely shallow-buffered datacenters. In INFOCOM (2020).
[11]
Cho, I., Jang, K., and Han, D. Credit-scheduled delay-bounded congestion control for datacenters. In SIGCOMM (2017).
[12]
Dukkipati, N., Refice, T., Cheng, Y., Chu, J., Herbert, T., Agarwal, A., Jain, A., and Sutin, N. An argument for increasing TCP's initial congestion window. ACM SIGCOMM Computer Communication Review 40, 3 (2010), 26--33.
[13]
Greenberg, A., Hamilton, J. R., Jain, N., Kandula, S., Kim, C., Lahiri, P., Maltz, D. A., Patel, P., and Sengupta, S. VL2: A scalable and flexible data center network. In SIGCOMM (2009).
[14]
Grossman, L. Large receive offload implementation in neterion 10gbe ethernet driver. In Linux Symposium (2005), p. 195.
[15]
Handley, M., Raiciu, C., Agache, A., Voinescu, A., Moore, A. W., Antichi, G., and Wójcik, M. Re-architecting datacenter networks and stacks for low latency and high performance. In SIGCOMM (2017).
[16]
Høiland-Jørgensen, T., Brouer, J. D., Borkmann, D., Fastabend, J., Herbert, T., Ahern, D., and Miller, D. The express data path: Fast programmable packet processing in the operating system kernel. In CoNEXT (2018).
[17]
Hu, S., Bai, W., Zeng, G., Wang, Z., Qiao, B., Chen, K., Tan, K., and Wang, Y. Aeolus: A Building Block for Proactive Transport in Datacenters. In SIGCOMM (2020).
[18]
Jorgensen, S., Holodnak, J., Dempsey, J., de Souza, K., Raghunath, A., Rivet, V., DeMoes, N., Alejos, A., and Wollaber, A. Extensible machine learning for encrypted network traffic application labeling via uncertainty quantification. IEEE Transactions on Artificial Intelligence (2023).
[19]
Judd, G. Attaining the Promise and Avoiding the Pitfalls of TCP in the Datacenter. In NSDI (2015).
[20]
Kaufmann, A., Stamler, T., Peter, S., Sharma, N. K., Krishnamurthy, A., and Anderson, T. TAS: TCP acceleration as an OS service. In EuroSys (2019).
[21]
Kumar, G., Dukkipati, N., Jang, K., Wassel, H. M., Wu, X., Montazeri, B., Wang, Y., Springborn, K., Alfeld, C., Ryan, M., et al. Swift: Delay is simple and effective for congestion control in the datacenter. In Proceedings of ACM SIGCOMM (2020).
[22]
Lee, C., Park, C., Jang, K., Moon, S., and Han, D. Accurate latency-based congestion feedback for datacenters. In ATC (2015).
[23]
Li, Q., Dong, M., and Godfrey, P. B. Halfback: Running short flows quickly and safely. In CoNEXT (2015).
[24]
Li, W., Xie, X., Liu, Y., Li, K., Chen, K., Ge, Z., Qi, H., Zhang, S., and Liu, G. Flow scheduling with imprecise knowledge. In Proceedings of USENIX NSDI (2024).
[25]
Li, Y., Miao, R., Liu, H. H., Zhuang, Y., Feng, F., Tang, L., Cao, Z., Zhang, M., Kelly, F., Alizadeh, M., et al. HPCC: High precision congestion control. In SIGCOMM (2019).
[26]
Liu, D., Allman, M., Jin, S., and Wang, L. Congestion control without a startup phase. In Proc. PFLDnet (2007).
[27]
McCanne, S., and Jacobson, V. The BSD Packet Filter: A New Architecture for User-level Packet Capture. In USENIX winter (1993), vol. 46.
[28]
Meng, T., Schiff, N. R., Godfrey, P. B., and Schapira, M. Pcc proteus: Scavenger transport and beyond. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication (2020), pp. 615--631.
[29]
Mittal, R., Lam, V. T., Dukkipati, N., Blem, E., Wassel, H., Ghobadi, M., Vahdat, A., Wang, Y., Wetherall, D., and Zats, D. TIMELY: RTT-based congestion control for the datacenter. In SIGCOMM (2015).
[30]
Mittal, R., Sherry, J., Ratnasamy, S., and Shenker, S. Recursively cautious congestion control. In NSDI (2014).
[31]
Mohammad, A., Adel, J., and Balaji, P. Analysis of DCTCP. ACM SIGMETRICS Performance Evaluation Review (2011).
[32]
Montazeri, B., Li, Y., Alizadeh, M., and Ousterhout, J. Homa: A receiver-driven low-latency transport protocol using network priorities. In SIGCOMM (2018).
[33]
Ousterhout, J. A linux kernel implementation of the homa transport protocol. In 2021 USENIX Annual Technical Conference (USENIX ATC 21) (2021), pp. 99--115.
[34]
Roy, A., Zeng, H., Bagga, J., Porter, G., and Snoeren, A. C. Inside the social network's (datacenter) network. In SIGCOMM (2015).
[35]
Singh, A., Ong, J., Agarwal, A., Anderson, G., Armistead, A., Bannon, R., Boving, S., Desai, G., Felderman, B., Germano, P., et al. Jupiter rising: A decade of clos topologies and centralized control in google's datacenter network. In SIGCOMM (2015).
[36]
Vamanan, B., Hasan, J., and Vijaykumar, T. Deadline-aware datacenter tcp (d2tcp). In SIGCOMM (2012).
[37]
Vanini, E., Pan, R., Alizadeh, M., Taheri, P., and Edsall, T. Let it flow: Resilient asymmetric load balancing with flowlet switching. In NSDI (2017).
[38]
Wang, Z., Luo, L., Ning, Q., Zeng, C., Li, W., Wan, X., Xie, P., Feng, T., Cheng, K., Geng, X., et al. {SRNIC}: A scalable architecture for {RDMA}{NICs}. In Proceedings of USENIX NSDI (2023).
[39]
Wu, H., Feng, Z., Guo, C., and Zhang, Y. Ictcp: Incast congestion control for tcp in data-center networks. IEEE/ACM transactions on networking 21, 2 (2012), 345--358.
[40]
Wu, H., Ju, J., Lu, G., Guo, C., Xiong, Y., and Zhang, Y. Tuning ECN for data center networks. In CoNEXT (2012).
[41]
Yasukata, K., Honda, M., Santry, D., and Eggert, L. StackMap:Low-Latency Networking with the OS Stack and Dedicated NICs. In ATC (2016).
[42]
Zhao, Y., Saeed, A., Zegura, E., and Ammar, M. Zd: A scalable zero-drop network stack at end hosts. In Proceedings of the 15th International Conference on Emerging Networking Experiments And Technologies (New York, NY, USA, 2019), CoNEXT '19, Association for Computing Machinery, p. 220--232.
[43]
Zhu, Y., Eran, H., Firestone, D., Guo, C., Lipshteyn, M., Liron, Y., Padhye, J., Raindel, S., Yahia, M. H., and Zhang, M. Congestion control for large-scale RDMA deployments. In SIGCOMM (2015).
Index Terms
- PPT: A Pragmatic Transport for Datacenters
Recommendations
PIAS: Practical Information-Agnostic Flow Scheduling for Data Center Networks
HotNets-XIII: Proceedings of the 13th ACM Workshop on Hot Topics in NetworksMany existing data center network (DCN) flow scheduling schemes minimize flow completion times (FCT) based on prior knowledge of flows and custom switch designs, making them hard to use in practice. This paper introduces, Pias, a practical flow ...
Scheduling Mix-flows in Commodity Datacenters with Karuna
SIGCOMM '16: Proceedings of the 2016 ACM SIGCOMM ConferenceCloud applications generate a mix of flows with and without deadlines. Scheduling such mix-flows is a key challenge; our experiments show that trivially combining existing schemes for deadline/non-deadline flows is problematic. For example, prioritizing ...
Deconstructing datacenter packet transport
HotNets-XI: Proceedings of the 11th ACM Workshop on Hot Topics in NetworksWe present, pFabric, a minimalistic datacenter fabric design that provides near-optimal performance in terms of completion time for high-priority flows and overall network utilization. pFabric's design eliminates nearly all buffering on switches (...
Comments
Information & Contributors
Information
Published In
August 2024
1033 pages
ISBN:9798400706141
DOI:10.1145/3651890
- Co-chairs:
- Aruna Seneviratne,
- Darryl Veitch,
- Program Co-chairs:
- Vyas Sekar,
- Minlan Yu
Copyright © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- NSFC
Conference
ACM SIGCOMM '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 462 of 3,389 submissions, 14%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 313Total Downloads
- Downloads (Last 12 months)313
- Downloads (Last 6 weeks)131
Reflects downloads up to 15 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in