Sándor Laki
ABSTRACT
In this paper, we propose the PVPIE Active Queue Management (AQM) method that combines the packet scheduling and dropping algorithms of PIE AQM and the packet marking-based resource sharing of the Per Packet Value (PPV) concept. The algorithm calculates dropping probabilities needed for keeping the queueing delay at a predefined level using the PIE algorithm. Then instead of applying this drop probability directly on incoming packets it translates the dropping probability to a Congestion Threshold Value (CTV) filter and drops (or marks) all incoming packets with Packet Value smaller than the threshold. The translation is based on statistics collected about Packet Values of incoming packets. Our evaluation based on simulations shows that PVPIE AQM combines the benefits of PIE and PPV concepts, keeping a target queueing delay and implementing policy-based resource sharing at the same time. The motivation for the proposed algorithm is simplicity and ease of deployment in real networks, since the schedulers of the original PPV approach need to perform drops from the middle of the queue. Such drops may be costly and may not be supported by current hardware.
- Study on architecture for next generation system. 3GPP TR 23.799, February 2016.Google Scholar
- Z. Cao, E. Zegura, and Z. Wang. Rainbow fair queueing: theory and applications. Computer Networks, 47(3):367--392, 2005. Google ScholarDigital Library
- K. De Schepper, O. Bondarenko, I.-J. Tsang, and B. Briscoe. Pi2: A linearized aqm for both classic and scalable tcp. In CoNEXT '16, pages 105--119, New York, NY, USA, 2016. ACM. Google ScholarDigital Library
- S. Floyd and V. Jacobson. Random early detection gateways for congestion avoidance. IEEE/ACM Trans. Netw., 1(4):397--413, Aug. 1993. Google ScholarDigital Library
- S. Ha, I. Rhee, and L. Xu. Cubic: A new tcp-friendly high-speed tcp variant. SIGOPS Oper. Syst. Rev., 42(5):64--74, July 2008. Google ScholarDigital Library
- T. R. Henderson, M. Lacage, G. F. Riley, C. Dowell, and J. Kopena. Network simulations with the ns-3 simulator. In Sigcomm (Demo), volume 14, 2008.Google Scholar
- S. Jansen and A. McGregor. Simulation with real world network stacks. In Simulation Conference, 2005 Proceedings of the Winter, pages 10--pp. IEEE, Dec 2005. Google ScholarDigital Library
- S. Nádas, Z. R. Turányi, and S. Rácz. Per packet value: A practical concept for network resource sharing. In IEEE Globecom 2016, 2016.Google Scholar
- K. Nichols and V. Jacobson. Controlling queue delay. Commun. ACM, 55(7):42--50, July 2012. Google ScholarDigital Library
- R. Pan, P. Natarajan, C. Piglione, M. S. Prabhu, V. Subramanian, F. Baker, and B. VerSteeg. Pie: A lightweight control scheme to address the bufferbloat problem. In IEEE HPSR, pages 148--155, July 2013.Google ScholarCross Ref
- D. Papadimitriou, M. Welzl, M. Scharf, and B. Briscoe. Open research issues in internet congestion control. Technical report, IRTF RFC 6077, February 2011.Google Scholar
- I. Stoica, S. Shenker, and H. Zhang. Core-stateless fair queueing: A scalable architecture to approximate fair bandwidth allocations in high-speed networks. IEEE/ACM Trans. Netw., 11(1):33--46, Feb. 2003. Google ScholarDigital Library
Index Terms
- Take your own share of the PIE
Recommendations
Towards a Congestion Control-Independent Core-Stateless AQM
ANRW '18: Proceedings of the Applied Networking Research WorkshopIn this paper, we propose CSAQM, a novel approach of Active Queue Management (AQM) for network traffic with multiple Congestion Control algorithms. Our goal is similar to that of PI2 AQM that supports both Classic and Scalable TCP in a single queue. In ...
Operating ranges, tunability and performance of CoDel and PIE
Bufferbloat is excessive delay due to the accumulation of packets in a routers oversized queues. CoDel and PIE are two recent Active Queue Management (AQM) algorithms that have been proposed to address bufferbloat by reducing the queuing delay while ...
To share or not to share: comparing burst buffer architectures
HPC '17: Proceedings of the 25th High Performance Computing SymposiumModern high performance computing platforms employ burst buffers to overcome the I/O bottleneck that limits the scale and efficiency of large-scale parallel computations. Currently there are two competing burst buffer architectures. One is to treat ...
Comments