【国民娱乐每日礼金gm777.top,国民彩票手机版app中大奖】我们为您提供国民彩票手机版app注册,国民彩票手机版app投注,国民彩票手机版appapp,国民彩票手机版app平台,巨华彩票开户,充提快速,操控简单,为国民彩票手机版app彩民服务!

學術報告
我的位置在: 国民彩票手机版app > 學術報告 > 正文
NitroSketch: Robust and General Sketch-based Monitoring in Software Switches
瀏覽次數:日期:2019-08-26編輯:信科院 科研辦

時間:201982715:00-17:00

地點:院樓 542 報告廳(原編號)

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.

報告人Alan (Zaoxing) Liuis a postdoctoral researcher at Carnegie Mellon University working with Vyas Sekar and Minlan Yu. He obtained his Ph.D. in Computer Science from Johns Hopkins University in Oct 2018. He is working in the areas of systems and networking, with a focus on network measurement, programmable networks, and distributed data processing. His research aims to build efficient networked systems with performance and theoretical guarantees, such as UnivMon, NitroSketch, DistCache, and ASAP. Liu’s research papers have been published in top venues in the field, including ACM SIGCOMM, USENIX OSDI, and FAST. As a leading author, he is a receipt of a USENIX FAST best paper award and an AT&T research best poster award. He is a contributor and developer of several open-source software packages for sketch-based streaming data analysis. As an early career researcher, he serves as a reviewer for ACM SOSR, VLDB, IEEE INFOCOM, TON, TKDE, and JSAC. His research is funded in part by NSF (SDI, IIS, EAGER), DARPA, Google, and Cisco.

国民彩票手机版app