کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6873415 | 1440636 | 2018 | 17 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Network measurement for 100 GbE network links using multicore processors
ترجمه فارسی عنوان
اندازه گیری شبکه برای لینک های 100 گیگابایتی با استفاده از پردازنده های چند هسته ای
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
نظریه محاسباتی و ریاضیات
چکیده انگلیسی
Network measurement has been playing a crucial role in network operations, since it cannot only detect the anomalies, but also facilitate traffic engineering. With the fast development of high speed network of 100Â Gbps and beyond, how to efficiently monitor and measure the network at flow granularity has become a challenging problem. Although there are dedicated network instrumentation appliances, the flexibility of defining measurement network tasks on a programmable platform is very attractive. In this study, we mainly focus on the evaluation of sketch-based network measurement using a multicore platform supported by Intel DPDK, a fast packet I/O library. We describe the versatile system level design options available for implementing such a programmable measurement platform for 100 GbE network links. Through extensive experiments, we investigate these design options and compare their trade-offs. Specifically, we evaluate the performance of the sketch-based measurement in terms of packet drop rate, processing time per packet and delay per packet. Based on the evaluation over the collected data, we propose the best practical measurement implementation to sustain the line rate while achieving the highest level of programmability.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Future Generation Computer Systems - Volume 79, Part 1, February 2018, Pages 180-189
Journal: Future Generation Computer Systems - Volume 79, Part 1, February 2018, Pages 180-189
نویسندگان
Xiaoban Wu, Peilong Li, Yongyi Ran, Yan Luo,