Zaoxing Liu
ABSTRACT
Software switches are emerging as a vital measurement vantage point in many networked systems. Sketching algorithms or sketches, provide high-fidelity approximate measurements, and appear as a promising alternative to traditional approaches such as packet sampling. However, sketches incur significant computation overhead in software switches. Existing efforts in implementing sketches in virtual switches make sacrifices on one or more of the following dimensions: performance (handling 40 Gbps line-rate packet throughput with low CPU footprint), robustness (accuracy guarantees across diverse workloads), and generality (supporting various measurement tasks).
In this work, we present the design and implementation of NitroSketch, a sketching framework that systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Our key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. We implement NitroSketch on three popular software platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS) and evaluate the performance. We show that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.
Supplemental Material
- Omid Alipourfard, Masoud Moshref, and Minlan Yu. 2015. Re-evaluating Measurement Algorithms in Software. In Proc. of ACM HotNets. Google Scholar
Digital Library
- Omid Alipourfard, Masoud Moshref, Yang Zhou, Tong Yang, and Minlan Yu. 2018. A Comparison of Performance and Accuracy of Measurement Algorithms in Software. In Proc. of ACM SOSR. Google ScholarDigital Library
- Mohammad Alizadeh, Tom Edsall, Sarang Dharmapurikar, Ramanan Vaidyanathan, Kevin Chu, Andy Fingerhut, Vinh The Lam, Francis Matus, Rong Pan, Navindra Yadav, and George Varghese. 2014. CONGA: Distributed Congestion-aware Load Balancing for Datacenters. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Mohammad Alizadeh, Shuang Yang, Milad Sharif, Sachin Katti, Nick McKeown, Balaji Prabhakar, and Scott Shenker. 2013. pFabric: Minimal Near-optimal Datacenter Transport. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Noga Alon, Yossi Matias, and Mario Szegedy. 1996. The Space Complexity of Approximating the Frequency Moments. In Proc. of ACM STOC. Google ScholarDigital Library
- Eran Assaf, Ran Ben-Basat, Gil Einziger, and Roy Friedman. 2018. Pay for a sliding bloom filter and get counting, distinct elements, and entropy for free. In Proc. of IEEE INFOCOM.Google ScholarCross Ref
- Ziv Bar-Yossef, T. S. Jayram, Ravi Kumar, D. Sivakumar, and Luca Trevisan. 2002. Counting Distinct Elements in a Data Stream. In Proc. of RANDOM. Google ScholarDigital Library
- Ran Ben Basat, Gil Einziger, Roy Friedman, Marcelo Caggiani Luizelli, and Erez Waisbard. 2017. Constant Time Updates in Hierarchical Heavy Hitters. In Proc. of ACM SIGCOMM and CoRR/1707.06778. Google ScholarDigital Library
- Ran Ben Basat, Gil Einziger, Roy Friedman, Marcelo Caggiani Luizelli, and Erez Waisbard. 2018. Volumetric Hierarchical Heavy Hitters. In Proc. of IEEE MASCOTS.Google ScholarCross Ref
- Ran Ben-Basat, Xiaoqi Chen, Gil Einziger, and Ori Rottenstreich. 2018. Efficient Measurement on Programmable Switches Using Probabilistic Recirculation. In Proc. of IEEE ICNP.Google ScholarCross Ref
- Theophilus Benson, Aditya Akella, and David A. Maltz. 2010. Network Traffic Characteristics of Data Centers in the Wild. In Proc. of ACM IMC. Google ScholarDigital Library
- Theophilus Benson, Ashok Anand, Aditya Akella, and Ming Zhang. 2011. MicroTE: Fine Grained Traffic Engineering for Data Centers. In Proc. of ACM CoNEXT. Google ScholarDigital Library
- Supratik Bhattacharyya, Andre Madeira, S. Muthukrishnan, and Tao Ye. 2007. How to Scalably and Accurately Skip Past Streams. In Proc. of IEEE ICDE. Google ScholarDigital Library
- CAIDA. 2016. The CAIDA UCSD Anonymized Internet Traces equinix-chicago. http://www.caida.org/data/passive/passive_2016_dataset.xmlGoogle Scholar
- CAIDA. 2018. The CAIDA UCSD Anonymized Internet Traces equinix-chicago. http://www.caida.org/data/passive/passive_dataset.xmlGoogle Scholar
- Cameron. 2015. Fast Concurrent Queue. https://github.com/cameron314/readerwriterqueueGoogle Scholar
- Moses Charikar, Kevin Chen, and Martin Farach-Colton. 2002. Finding Frequent Items in Data Streams. In Proc. of ICALP. Google ScholarDigital Library
- Xiaoqi Chen, Shir Landau Feibish, Yaron Koral, Jennifer Rexford, and Ori Rottenstreich. 2018. Catching the Microburst Culprits with Snappy. In Proc. of SelfDN Workshop. Google ScholarDigital Library
- Xiaoqi Chen, Shir Landau Feibish, Yaron Koral, Jennifer Rexford, Ori Rottenstreich, Steven A. Monetti, and Wang Tzuu-Yi. 2019. Fine-Grained Queue Measurement in the Data Plane. In Proc. of ACM CoNEXT.Google ScholarDigital Library
- Kenjiro Cho. 2017. Recursive Lattice Search: Hierarchical Heavy Hitters Revisited. In Proc. of ACM IMC. Google ScholarDigital Library
- Cisco. 2012. Introduction to Cisco IOS NetFlow. https://www.cisco.com/c/en/us/products/collateral/ios-nx-os-software/ios-netflow/prod_white_paper0900aecd80406232.htmlGoogle Scholar
- Cisco. 2015. Cisco Nexus 1000V Switch. https://www.cisco.com/c/en/us/products/switches/nexus-1000v-switch-vmware-vsphere/index.htmlGoogle Scholar
- Yann Collet. 2016. xxHash Library. http://www.xxhash.com/Google Scholar
- Gerald Combs. 1998. Wireshark. https://www.wireshark.orgGoogle Scholar
- Graham Cormode and Minos Garofalakis. 2007. Sketching Probabilistic Data Streams. In Proc. of ACM SIGMOD. Google ScholarDigital Library
- Graham Cormode, Flip Korn, S. Muthukrishnan, and Divesh Srivastava. 2008. Finding Hierarchical Heavy Hitters in Streaming Data. ACM Trans. Knowl. Discov. Data (2008). Google ScholarDigital Library
- Graham Cormode and S. Muthukrishnan. 2005. An Improved Data Stream Summary: The Count-Min Sketch and Its Applications. J. Algorithms (2005). Google ScholarDigital Library
- Andrew R. Curtis, Jeffrey C. Mogul, Jean Tourrilhes, Praveen Yalagandula, Puneet Sharma, and Sujata Banerjee. 2011. DevoFlow: Scaling Flow Management for High-performance Networks. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Intel Ethernet Networking Division. 2018. Intel Ethernet Controller 710 Series Datasheet. https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xl710-10-40-controller-datasheet.pdfGoogle Scholar
- Rick Durrett. 2010. Probability: Theory and Examples (4th ed.). Cambridge University Press. Google ScholarCross Ref
- Paul Emmerich, Sebastian Gallenmüller, Daniel Raumer, Florian Wohlfart, and Georg Carle. 2015. MoonGen: A Scriptable High-Speed Packet Generator. In Proc. of ACM IMC. Google ScholarDigital Library
- Zaoxing Liu et al. 2019. NitroSketch Source Code. https://github.com/zaoxing/NitroSketchGoogle Scholar
- Seyed K. Fayaz, Yoshiaki Tobioka, Vyas Sekar, and Michael Bailey. 2015. Bohatei: Flexible and Elastic DDoS Defense. In Proc. of USENIX Security. Google ScholarDigital Library
- FD.io. 2018. Vector Packet Processing. https://fd.io/technology/Google Scholar
- William Feller. 1943. Generalization of a Probability Limit Theorem of Cramér. Trans. Amer. Math. Soc. (1943).Google Scholar
- Pedro Garcia-Teodoro, Jesus E. Diaz-Verdejo, Gabriel Macia-Fernandez, and E. Vazquez. 2009. Anomaly-Based Network Intrusion Detection: Techniques, Systems and Challenges. Computers and Security (2009). Google ScholarDigital Library
- Robert D Gordon. 1941. Values of Mills' Ratio of Area to Bounding Ordinate and of the Normal Probability Integral for Large Values of the Argument. The Annals of Mathematical Statistics (1941).Google Scholar
- Arpit Gupta, Rob Harrison, Marco Canini, Nick Feamster, Jennifer Rexford, and Walter Willinger. 2018. Sonata: Query-Driven Streaming Network Telemetry. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Sangjin Han, Keon Jang, Aurojit Panda, Shoumik Palkar, Dongsu Han, and Sylvia Ratnasamy. 2015. SoftNIC: A Software NIC to Augment Hardware. Technical Report.Google Scholar
- Thomas Holterbach, Edgar Costa Molero, Maria Apostolaki, Alberto Dainotti, Stefano Vissicchio, and Laurent Vanbever. 2019. Blink: Fast Connectivity Recovery Entirely in the Data Plane. In Proc. of USENIX NSDI. Google ScholarDigital Library
- Nan Hua, Bill Lin, Jun (Jim) Xu, and Haiquan (Chuck) Zhao. 2008. BRICK: ANovel Exact Active Statistics Counter Architecture. In Proc. of ACM/IEEE ANCS. Google ScholarDigital Library
- Qi Huang, Ken Birman, Robbert van Renesse, Wyatt Lloyd, Sanjeev Kumar, and Harry C. Li. 2013. An Analysis of Facebook Photo Caching. In Proc. of ACM SOSP. Google ScholarDigital Library
- Qun Huang, Xin Jin, Patrick P. C. Lee, Runhui Li, Lu Tang, Yi-Chao Chen, and Gong Zhang. 2017. SketchVisor: Robust Network Measurement for Software Packet Processing. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Qun Huang, Patrick PC Lee, and Yungang Bao. 2018. SketchLearn: Relieving User Burdens in ApproximateMeasurement with Automated Statistical Inference. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Intel. 2012. Intel Advanced Vector Extensions. https://software.intel.com/en-us/isa-extensions/intel-avxGoogle Scholar
- Intel. 2018. Intel VTune Amplifier. https://software.intel.com/en-us/vtuneGoogle Scholar
- T. S. Jayram, Andrew McGregor, S. Muthukrishnan, and Erik Vee. 2007. Estimating Statistical Aggregates on Probabilistic Data Streams. Proc. of ACM PODS (2007). Google ScholarDigital Library
- Xin Jin, Xiaozhou Li, Haoyu Zhang, Robert Soulé, Jeongkeun Lee, Nate Foster, Changhoon Kim, and Ion Stoica. 2017. NetCache: Balancing Key-Value Stores with Fast In-Network Caching. In Proc. of ACM SOSP. Google ScholarDigital Library
- Abdul Kabbani, Mohammad Alizadeh, Masato Yasuda, Rong Pan, and Balaji Prabhakar. 2010. AF-QCN: Approximate Fairness with Quantized Congestion Notification for Multi-tenanted Data Centers. In Prof. of IEEE HOTI. Google ScholarDigital Library
- Maurice George Kendall, Alan Stuart, and Keith Ord. 1987. Kendall's Advanced Theory of Statistics. Oxford University Press, Inc. Google ScholarDigital Library
- Balachander Krishnamurthy, Subhabrata Sen, Yin Zhang, and Yan Chen. 2003. Sketch-based Change Detection: Methods, Evaluation, and Applications. In Proc. of ACM IMC. Google ScholarDigital Library
- Ashwin Lall, Vyas Sekar, Mitsunori Ogihara, Jun Xu, and Hui Zhang. 2006. Data Streaming Algorithms for Estimating Entropy of Network Traffic. In Proc. of ACM SIGMETRICS/Performance. Google ScholarDigital Library
- Junda Liu, Aurojit Panda, Ankit Singla, Brighten Godfrey, Michael Schapira, and Scott Shenker. 2013. Ensuring Connectivity via Data Plane Mechanisms. In Proc. of USENIX NSDI. Google ScholarDigital Library
- Zaoxing Liu, Zhihao Bai, Zhenming Liu, Xiaozhou Li, Changhoon Kim, Vladimir Braverman, Xin Jin, and Ion Stoica. 2019. DistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed Caching. In Proc. of USENIX FAST. Google ScholarDigital Library
- Zaoxing Liu, Antonis Manousis, Gregory Vorsanger, Vyas Sekar, and Vladimir Braverman. 2016. One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Zaoxing Liu, Greg Vorsanger, Vladimir Braverman, and Vyas Sekar. 2015. Enabling a "RISC" Approach for Software-Defined Monitoring Using Universal Streaming. In Proc. of ACM HotNets. Google ScholarDigital Library
- Yi Lu, Andrea Montanari, Balaji Prabhakar, Sarang Dharmapurikar, and Abdul Kabbani. 2008. Counter Braids: A Novel Counter Architecture for PerFlowMeasurement. In Proc. of ACM SIGMETRICS. Google ScholarDigital Library
- MACCDC. 2012. Capture Traces from Mid-Atlantic CCDC. http://www.netresec.com/?page=MACCDCGoogle Scholar
- Jiri Matousek and Jan Vondrak. 2008. The Probabilistic Method-Lecture Notes. http://www.cs.cmu.edu/~15850/handouts/matousek-vondrak-prob-ln.pdfGoogle Scholar
- Andrew McGregor, A Pavan, Srikanta Tirthapura, and David P. Woodruff. 2016. Space-Efficient Estimation of Statistics Over Sub-Sampled Streams. Algorithmica (2016). Google ScholarDigital Library
- Ahmed Metwally, Divyakant Agrawal, and Amr El Abbadi. 2005. Efficient Computation of Frequent and Top-k Elements in Data Streams. In Proc. of ICDT. Google ScholarDigital Library
- Microsoft. 2016. Hyper-V Virtual Switch Overview. https://technet.microsoft.com/en-us/library/hh831823.aspxGoogle Scholar
- Jayadev Misra and David Gries. 1982. Finding Repeated Elements. Technical Report. Google ScholarDigital Library
- M. Mitzenmacher, T. Steinke, and J. Thaler. 2012. Hierarchical Heavy Hitters with the Space Saving Algorithm. In Proc. of ALENEX. Google ScholarDigital Library
- Srinivas Narayana, Anirudh Sivaraman, Vikram Nathan, Prateesh Goyal, Venkat Arun, Mohammad Alizadeh, Vimalkumar Jeyakumar, and Changhoon Kim. 2017. Language-Directed Hardware Design for Network Performance Monitoring. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- George Nychis, Vyas Sekar, David G. Andersen, Hyong Kim, and Hui Zhang. 2008. An Empirical Evaluation of Entropy-based Traffic Anomaly Detection. In Proc. of ACM IMC. Google ScholarDigital Library
- Ben Pfaff, Justin Pettit, Teemu Koponen, Ethan Jackson, Andy Zhou, Jarno Rajahalme, Jesse Gross, Alex Wang, Joe Stringer, Pravin Shelar, Keith Amidon, and Martin Casado. 2015. The Design and Implementation of Open vSwitch. In Proc. of USENIX NSDI. Google ScholarDigital Library
- Robert Schweller, Ashish Gupta, Elliot Parsons, and Yan Chen. 2004. Reversible Sketches for Efficient and Accurate Change Detection over Network Data Streams. In Proc. of ACM IMC. Google ScholarDigital Library
- Vibhaalakshmi Sivaraman, Srinivas Narayana, Ori Rottenstreich, S. Muthukrishnan, and Jennifer Rexford. 2017. Heavy-Hitter Detection Entirely in the Data Plane. In Proc. of ACM SOSR. Google ScholarDigital Library
- Eric V Slud. 1977. Distribution inequalities for the binomial law. The Annals of Probability (1977).Google Scholar
- Mea Wang, Baochun Li, and Zongpeng Li. 2004. sFlow: Towards Resource-Efficient and Agile Service Federation in Service Overlay Networks. In Proc. of IEEE ICDCS. Google ScholarDigital Library
- Li Yang, Wu Hao, Pan Tian, Dai Huichen, Lu Jianyuan, and Liu Bin. 2016. CASE: Cache-assisted Stretchable Estimator for High Speed Per-flow Measurement. In Proc. of IEEE INFOCOM.Google Scholar
- Tong Yang, Jie Jiang, Peng Liu, Qun Huang, Junzhi Gong, Yang Zhou, Rui Miao, Xiaoming Li, and Steve Uhlig. 2018. Elastic Sketch: Adaptive and Fast Network-wide Measurements. In Proc. of ACM SIGCOMM. Google ScholarDigital Library
- Lei Ying, R. Srikant, and Xiaohan Kang. 2015. The Power of Slightly More than One Sample in Randomized Load Balancing. In Proc. of IEEE INFOCOM.Google ScholarCross Ref
- Da Yu, Yibo Zhu, Behnaz Arzani, Rodrigo Fonseca, Tianrong Zhang, Karl Deng, and Lihua Yuan. 2019. dShark: A General, Easy to Program and Scalable Framework for Analyzing In-network Packet Traces. In Proc. of USENIX NSDI. Google ScholarDigital Library
- Minlan Yu, Lavanya Jose, and Rui Miao. 2013. Software Defined Traffic Measurement with OpenSketch. In Proc. of USENIX NSDI. Google ScholarDigital Library
Index Terms
- Nitrosketch: robust and general sketch-based monitoring in software switches
Recommendations
Fast In-kernel Traffic Sketching in eBPF
The extended Berkeley Packet Filter (eBPF) is an infrastructure that allows to dynamically load and run micro-programs directly in the Linux kernel without recompiling it.
In this work, we study how to develop high-performance network measurements in ...
Accelerating Open vSwitch with Integrated GPU
KBNets '17: Proceedings of the Workshop on Kernel-Bypass NetworksWith the fast development of Software Defined Networking (SDN) and network virtualization, software-based network virtual switches have emerged as a critical component to provide network services to VMs. Among virtual switches, Open vSwitch (OvS) is an ...
KVS: high-efficiency kernel-level virtual switch
SoCC '17: Proceedings of the 2017 Symposium on Cloud ComputingIn clouds, virtual switch (vSwitch) is in charge of packet forwarding between virtual machines (VMs). However, kernel-based vSwitches show throughput degradation for intensive packet processing; this becomes a bottleneck for the network performance of ...
Comments