Srinivas Narayana
ABSTRACT
Network performance monitoring today is restricted by existing switch support for measurement, forcing operators to rely heavily on endpoints with poor visibility into the network core. Switch vendors have added progressively more monitoring features to switches, but the current trajectory of adding specific features is unsustainable given the ever-changing demands of network operators. Instead, we ask what switch hardware primitives are required to support an expressive language of network performance questions. We believe that the resulting switch hardware design could address a wide variety of current and future performance monitoring needs.
We present a performance query language, Marple, modeled on familiar functional constructs like map, filter, groupby, and zip. Marple is backed by a new programmable key-value store primitive on switch hardware. The key-value store performs flexible aggregations at line rate (e.g., a moving average of queueing latencies per flow), and scales to millions of keys. We present a Marple compiler that targets a P4-programmable software switch and a simulator for high-speed programmable switches. Marple can express switch queries that could previously run only on end hosts, while Marple queries only occupy a modest fraction of a switch's hardware resources.
Supplemental Material
- 45 nanometer - Wikipedia, Technology demos. https://en.wikipedia.org/wiki/45_nanometer#Technology_demos.Google Scholar
- An Update on the Memcached/Redis Benchmark. http://oldblog.antirez.com/post/update-on-memcached-redis-benchmark.html.Google Scholar
- Barefoot: The World's Fastest and Most Programmable Networks. https://barefootnetworks.com/media/white_papers/Barefoot-Worlds-Fastest-Most-Programmable-Networks.pdf.Google Scholar
- Benchmarking Apache Kafka: 2 Million Writes Per Second (On Three Cheap Machines). https://engineering.linkedin.com/kafka/benchmarking-apache-kafka-2-million-writes-second-three-cheap-machines.Google Scholar
- Broadcom First to Deliver 64 Ports of 100GE with Tomahawk II 6.4Tbps Ethernet Switch. https://www.broadcom.com/news/product-releases/broadcom-first-to-deliver-64-ports-of-100ge-with-tomahawk-ii-ethernet-switch.Google Scholar
- Cavium XPliant Switches and Microsoft Azure Networking Achieve SAI Routing Interoperability. http://www.cavium.com/newsevents-Cavium-XPliant-Switches-and-Microsoft-Azure-Networking-Achieve-SAI-Routing-Interoperability.html.Google Scholar
- Cisco IOS NetFlow. http://www.cisco.com/c/en/us/products/ios-nx-os-software/ios-netflow/index.html.Google Scholar
- Configuring SPAN. http://www.cisco.com/c/en/us/td/docs/switches/lan/catalyst2940/software/release/12-1_19_ea1/configuration/guide/2940scg_1/swspan.html.Google Scholar
- Data center flow telemetry. http://www.cisco.com/c/en/us/products/collateral/data-center-analytics/tetration-analytics/white-paper-c11-737366.html.Google Scholar
- Gigamon. https://www.gigamon.com/products/visibility-nodes/visibility-appliances.html.Google Scholar
- How Fast is Redis? http://redis.io/topics/benchmarks.Google Scholar
- In-band Network Telemetry. https://github.com/p4lang/p4factory/tree/master/apps/int.Google Scholar
- Intel FlexPipe. http://www.intel.com/content/dam/www/public/us/en/documents/product-briefs/ethernet-switch-fm6000-series-brief.pdf.Google Scholar
- Intel64 and IA-32 Architectures Optimization Reference Manual. http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf.Google Scholar
- Marple proofs. http://web.mit.edu/marple/marple_tr.pdf.Google Scholar
- Microsoft bets big on SDN. https://azure.microsoft.com/en-us/blog/microsoft-showcases-software-defined-networking-innovation-at-sigcomm-v2/.Google Scholar
- Multiply-accumulate operation. https://en.wikipedia.org/wiki/Multiply-accumulate_operation.Google Scholar
- P4-16 Language Specification. http://p4.org/wp-content/uploads/2016/12/P4_16-prerelease-Dec_16.html.Google Scholar
- P4 Behavioral Model. https://github.com/p4lang/behavioral-model.Google Scholar
- Redis. http://redis.io/.Google Scholar
- sFlow. https://en.wikipedia.org/wiki/SFlow.Google Scholar
- SRAM - ARM. https://www.arm.com/products/physical-ip/embedded-memory-ip/sram.php.Google Scholar
- The CAIDA UCSD Anonymized Internet Traces 2014 - June. http://www.caida.org/data/passive/passive_2014_dataset.xml.Google Scholar
- The CAIDA UCSD Anonymized Internet Traces 2016 - April. http://www.caida.org/data/passive/passive_2016_dataset.xml.Google Scholar
- XPliant™ Ethernet Switch Product Family. http://www.cavium.com/XPliant-Ethernet-Switch-Product-Family.html.Google Scholar
- The Future of Network Monitoring with Barefoot Networks. https://youtu.be/Gbm7kDHXR-o, 2017.Google Scholar
- M. Alizadeh, T. Edsall, S. Dharmapurikar, R. Vaidyanathan, K. Chu, A. Fingerhut, V. T. Lam, F. Matus, R. Pan, N. Yadav, and G. Varghese. CONGA: Distributed Congestion-Aware Load Balancing for Datacenters. In SIGCOMM, 2014.Google ScholarDigital Library
- Alizadeh, Mohammad. Empirical Traffic Generator. https://github.com/datacenter/empirical-traffic-gen, 2017.Google Scholar
- J. R. Allen, K. Kennedy, C. Porterfield, and J. Warren. Conversion of Control Dependence to Data Dependence. In POPL, 1983. Google ScholarDigital Library
- A. Arasu, S. Babu, and J. Widom. The CQL Continuous Query Language: Semantic Foundations and Query Execution. The VLDB Journal, 2006. Google ScholarDigital Library
- B. Arzani, S. Ciraci, B. T. Loo, A. Schuster, and G. Outhred. Taking the Blame Game out of Data Centers Operations with NetPoirot. In Proceedings of the 2016 Conference on ACM SIGCOMM 2016 Conference, SIGCOMM '16, 2016. Google ScholarDigital Library
- T. Benson, A. Akella, and D. A. Maltz. Network Traffic Characteristics of Data Centers in the Wild. ACM International Measurement Conference, Nov. 2010. Google ScholarDigital Library
- P. Bosshart, G. Gibb, H.-S. Kim, G. Varghese, N. McKeown, M. Izzard, F. Mujica, and M. Horowitz. Forwarding Metamorphosis: Fast Programmable Match-Action Processing in Hardware for SDN. In SIGCOMM, 2013.Google ScholarDigital Library
- G. Cormode and S. Muthukrishnan. An Improved Data Stream Summary: The Count-Min Sketch and Its Applications. Journal of Algorithms, 2005. Google ScholarDigital Library
- C. Cranor, T. Johnson, O. Spataschek, and V. Shkapenyuk. Gigascope: A Stream Database for Network Applications. In SIGMOD, 2003. Google ScholarDigital Library
- D. R. Ditzel and D. A. Patterson. Retrospective on High-level Language Computer Architecture. In ISCA, 1980. Google ScholarDigital Library
- M. Dobrescu, K. Argyraki, and S. Ratnasamy. Toward Predictable Performance in Software Packet-processing Platforms. In NSDI, 2012.Google ScholarDigital Library
- N. Foster, R. Harrison, M. J. Freedman, C. Monsanto, J. Rexford, A. Story, and D. Walker. Frenetic: A Network Programming Language. In ICFP, 2011. Google ScholarDigital Library
- G. Gibb, G. Varghese, M. Horowitz, and N. McKeown. Design Principles for Packet Parsers. In ANCS, 2013. Google ScholarCross Ref
- C. Guo, L. Yuan, D. Xiang, Y. Dang, R. Huang, D. Maltz, Z. Liu, V. Wang, B. Pang, H. Chen, Z.-W. Lin, and V. Kurien. Pingmesh: A Large-Scale System for Data Center Network Latency Measurement and Analysis. In SIGCOMM, 2015. Google ScholarDigital Library
- A. Gupta, R. Birkner, M. Canini, N. Feamster, C. Mac-Stoker, and W. Willinger. Network Monitoring is a Streaming Analytics Problem. In HOTNETS, 2016. Google ScholarDigital Library
- N. Handigol, B. Heller, V. Jeyakumar, D. Mazières, and N. McKeown. I Know What Your Packet Did Last Hop: Using Packet Histories to Troubleshoot Networks. In NSDI, 2014.Google ScholarDigital Library
- S. Hart, E. Frachtenberg, and M. Berezecki. Predicting Memcached Throughput Using Simulation and Modeling. In Symposium on Theory of Modeling and Simulation, 2012.Google ScholarDigital Library
- V. Jeyakumar, M. Alizadeh, Y. Geng, C. Kim, and D. Mazières. Millions of Little Minions: Using Packets for Low Latency Network Programming and Visibility. In SIGCOMM, 2014. Google ScholarDigital Library
- S. P. Jones and P. Wadler. Comprehensive Comprehensions. In Proceedings of the ACM SIGPLAN Workshop on Haskell Workshop, 2007. Google ScholarDigital Library
- M. Kumar and K. Prasad. Auto-learning of MAC addresses and lexicographic lookup of hardware database. US Patent App. 10/747,332.Google Scholar
- B. Lantz, B. Heller, and N. McKeown. A Network in a Laptop: Rapid Prototyping for Software-defined Networks. In HotNets, 2010. Google ScholarDigital Library
- Y. Li, R. Miao, C. Kim, and M. Yu. FlowRadar: A Better NetFlow for Data Centers. In NSDI, 2016.Google ScholarDigital Library
- Z. Liu, A. Manousis, G. Vorsanger, V. Sekar, and V. Braverman. One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon. In SIGCOMM, 2016.Google ScholarDigital Library
- W. M. McKeeman. Language directed computer design. In Proceedings of the November 14-16, 1967, fall joint computer conference, 1967. Google ScholarDigital Library
- N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner. OpenFlow: Enabling Innovation in Campus Networks. SIGCOMM Comput. Commun. Rev., 38(2):69--74, Mar. 2008. Google ScholarDigital Library
- M. Moshref, M. Yu, R. Govindan, and A. Vahdat. DREAM: Dynamic Resource Allocation for Software-defined Measurement. In SIGCOMM, 2014.Google ScholarDigital Library
- M. Moshref, M. Yu, R. Govindan, and A. Vahdat. Trumpet: Timely and Precise Triggers in Data Centers. In SIGCOMM, 2016.Google ScholarDigital Library
- S. Narayana, M. Tahmasbi, J. Rexford, and D. Walker. Compiling Path Queries. In NSDI, 2016.Google ScholarDigital Library
- P. Phaal. SFlow sampling rates, 2016. http://blog.sflow.com/2009/06/sampling-rates.html.Google Scholar
- A. Sivaraman, A. Cheung, M. Budiu, C. Kim, M. Alizadeh, H. Balakrishnan, G. Varghese, N. McKeown, and S. Licking. Packet Transactions: High-Level Programming for Line-Rate Switches. In SIGCOMM, 2016.Google ScholarDigital Library
- A. Sivaraman, S. Subramanian, M. Alizadeh, S. Chole, S.-T. Chuang, A. Agrawal, H. Balakrishnan, T. Edsall, S. Katti, and N. McKeown. Programmable Packet Scheduling at Line Rate. In SIGCOMM, 2016. Google ScholarDigital Library
- P. Tammana, R. Agarwal, and M. Lee. Simplifying Datacenter Network Debugging with PathDump. In OSDI, 2016.Google ScholarDigital Library
- D. Ungar, R. Blau, P. Foley, D. Samples, and D. Patterson. Architecture of SOAR: Smalltalk on a RISC. In ISCA, 1984.Google Scholar
- E. Vanini, R. Pan, M. Alizadeh, P. Taheri, and T. Edsall. Let it Flow: Resilient Asymmetric Load Balancing with Flowlet Switching. In NSDI, 2017.Google Scholar
- V. Vasudevan, A. Phanishayee, H. Shah, E. Krevat, D. G. Andersen, G. R. Ganger, G. A. Gibson, and B. Mueller. Safe and Effective Fine-Grained TCP Retransmissions for Datacenter Communication. In SIGCOMM, 2009. Google ScholarDigital Library
- M. Yu, A. Greenberg, D. Maltz, J. Rexford, L. Yuan, S. Kandula, and C. Kim. Profiling Network Performance for Multi-tier Data Center Applications. In NSDI, 2011.Google ScholarDigital Library
- M. Yu, L. Jose, and R. Miao. Software Defined Traffic Measurement with OpenSketch. In NSDI, 2013.Google ScholarDigital Library
- M. Zaharia, T. Das, H. Li, T. Hunter, S. Shenker, and I. Stoica. Discretized Streams: Fault-tolerant Streaming Computation at Scale. In SOSP, 2013.Google ScholarDigital Library
- Y. Zhu, N. Kang, J. Cao, A. Greenberg, G. Lu, R. Mahajan, D. Maltz, L. Yuan, M. Zhang, B. Y. Zhao, and H. Zheng. Packet-Level Telemetry in Large Datacenter Networks. In SIGCOMM, 2015. Google ScholarDigital Library
Index Terms
- Language-Directed Hardware Design for Network Performance Monitoring
Recommendations
Demonstration of the Marple System for Network Performance Monitoring
SIGCOMM Posters and Demos '17: Proceedings of the SIGCOMM Posters and DemosWe demonstrate Marple [15], a system that allows network operators to measure a wide variety of performance metrics in real time. It consists of a performance query language, Marple, modeled on familiar functional operators like map, filter, and ...
Precise Time-synchronization in the Data-Plane using Programmable Switching ASICs
SOSR '19: Proceedings of the 2019 ACM Symposium on SDN ResearchCurrent implementations of time synchronization protocols (e.g. PTP) in standard industry-grade switches handle the protocol stack in the slow-path (control-plane). With new use cases of in-network computing using programmable switching ASICs, global ...
eHDL: Turning eBPF/XDP Programs into Hardware Designs for the NIC
ASPLOS 2023: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3Scaling network packet processing performance to meet the increasing speed of network ports requires software programs to carefully leverage the network devices’ hardware features. This is a complex task for network programmers, who need to learn and ...
Comments