Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.00023
Stefan Geissler, Stanislav Lange, Florian Wamser, T. Hossfeld
From the point of view of telecommunication providers, video streaming is one of the most demanding applications in today's Internet. Over 73% of the total global network traffic has been attributed to video streaming applications in 2017. In this work, we provide a first step towards a better understanding of the packet level behavior of video streaming traffic to enable more efficient traffic engineering in the future. We perform a measurement study with the popular video streaming platform YouTube and show that the different playout phases of a video streaming session can not only be observed by evaluating application layer metrics, but also from raw and encrypted packet level traces.
{"title":"Deriving YouTube Playout Phases from Encrypted Packet Level Traffic","authors":"Stefan Geissler, Stanislav Lange, Florian Wamser, T. Hossfeld","doi":"10.1109/ITC30.2018.00023","DOIUrl":"https://doi.org/10.1109/ITC30.2018.00023","url":null,"abstract":"From the point of view of telecommunication providers, video streaming is one of the most demanding applications in today's Internet. Over 73% of the total global network traffic has been attributed to video streaming applications in 2017. In this work, we provide a first step towards a better understanding of the packet level behavior of video streaming traffic to enable more efficient traffic engineering in the future. We perform a measurement study with the popular video streaming platform YouTube and show that the different playout phases of a video streaming session can not only be observed by evaluating application layer metrics, but also from raw and encrypted packet level traces.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134373265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.10059
Paul Nikolaus, Sebastian A. Henningsen, Michael A. Beck, J. Schmitt
Stochastic network calculus (SNC) is a versatile framework to derive probabilistic performance bounds. Recently, it was proposed in [1] to replace the typical a priori assumptions on arrival processes with measurement observations and to incorporate the corresponding statistical uncertainty into calculation of the bounds. This so-called statistical network calculus (StatNC) opens the door for many applications with limited traffic information. However, the important traffic class of self-similar processes such as fractional Brownian Motion (fBm) was left open in [1], thus, e.g., depriving the usage of the StatNC for Internet traffic. In this work, we close this gap by integrating fBm arrivals into the StatNC. To this end, we analyze the impact imposed by the uncertainty on the backlog bound and show in numerical evaluations that the additional inaccuracy is only of moderate size.
{"title":"Integrating Fractional Brownian Motion Arrivals into the Statistical Network Calculus","authors":"Paul Nikolaus, Sebastian A. Henningsen, Michael A. Beck, J. Schmitt","doi":"10.1109/ITC30.2018.10059","DOIUrl":"https://doi.org/10.1109/ITC30.2018.10059","url":null,"abstract":"Stochastic network calculus (SNC) is a versatile framework to derive probabilistic performance bounds. Recently, it was proposed in [1] to replace the typical a priori assumptions on arrival processes with measurement observations and to incorporate the corresponding statistical uncertainty into calculation of the bounds. This so-called statistical network calculus (StatNC) opens the door for many applications with limited traffic information. However, the important traffic class of self-similar processes such as fractional Brownian Motion (fBm) was left open in [1], thus, e.g., depriving the usage of the StatNC for Internet traffic. In this work, we close this gap by integrating fBm arrivals into the StatNC. To this end, we analyze the impact imposed by the uncertainty on the backlog bound and show in numerical evaluations that the additional inaccuracy is only of moderate size.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115576562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/itc30.2018.00002
{"title":"[Copyright notice]","authors":"","doi":"10.1109/itc30.2018.00002","DOIUrl":"https://doi.org/10.1109/itc30.2018.00002","url":null,"abstract":"","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124089970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/itc30.2018.00004
{"title":"Welcome Message from the ITC 30 General Co-Chairs","authors":"","doi":"10.1109/itc30.2018.00004","DOIUrl":"https://doi.org/10.1109/itc30.2018.00004","url":null,"abstract":"","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129674604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.10060
Fabien Geyer, G. Carle
Deterministic network calculus offers a framework for providing guaranteed bounds on end-to-end delay and buffer usage in computer networks. Various network analysis methods have been proposed in order to reduce the impact of burstiness or multiplexing and provide tight performance bounds. Yet, the choice of which analysis method to use given a network to analyze is not straightforward as it has been shown in the literature that corner cases exist leading to poor tightness. We propose in this paper to take a new look at this question using insights from data and confirm that there is no clear winner when deciding which method to use. Based on those first results, we make the case for a network calculus heuristic in order to predict the bounds produced by a given network analysis method. Our main contribution is a heuristic based on graph-based deep learning, which is able to directly process networks of servers and flows. Via a numerical evaluation, we show that our proposed heuristic is able to accurately predict which analysis method will produce the tightest delay bound. We also demonstrate that the computational cost of our heuristic makes it of practical use, with average runtimes one or two order of magnitude faster than traditional analysis methods.
{"title":"The Case for a Network Calculus Heuristic: Using Insights from Data for Tighter Bounds","authors":"Fabien Geyer, G. Carle","doi":"10.1109/ITC30.2018.10060","DOIUrl":"https://doi.org/10.1109/ITC30.2018.10060","url":null,"abstract":"Deterministic network calculus offers a framework for providing guaranteed bounds on end-to-end delay and buffer usage in computer networks. Various network analysis methods have been proposed in order to reduce the impact of burstiness or multiplexing and provide tight performance bounds. Yet, the choice of which analysis method to use given a network to analyze is not straightforward as it has been shown in the literature that corner cases exist leading to poor tightness. We propose in this paper to take a new look at this question using insights from data and confirm that there is no clear winner when deciding which method to use. Based on those first results, we make the case for a network calculus heuristic in order to predict the bounds produced by a given network analysis method. Our main contribution is a heuristic based on graph-based deep learning, which is able to directly process networks of servers and flows. Via a numerical evaluation, we show that our proposed heuristic is able to accurately predict which analysis method will produce the tightest delay bound. We also demonstrate that the computational cost of our heuristic makes it of practical use, with average runtimes one or two order of magnitude faster than traditional analysis methods.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134401375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.00022
Florian Metzger, Roman Heger
This paper explores the full chain of lag contribution factors in a specific online multiplayer game, namely Overwatch: From the creation of input events, over the network, and back to displaying the results on the local screen. Together they result in the dreaded end-to-end lag, which has a direct impact on the subjective quality one experiences when playing video games. In its investigation, this paper reveals surprising effects in the game's networking behavior that are omitted when colloquially talking about, e.g. a 60 Hz update rate, but must be considered nonetheless. These insights, gained from examining network traces of Overwatch matches that were played on a realistic, resource constrained PC, can then be used to refine end-to-end lag simulation models and reach a better understanding of all responsible lag components.
{"title":"Exploring the Transmission Behaviour of Overwatch: The Source of Lag","authors":"Florian Metzger, Roman Heger","doi":"10.1109/ITC30.2018.00022","DOIUrl":"https://doi.org/10.1109/ITC30.2018.00022","url":null,"abstract":"This paper explores the full chain of lag contribution factors in a specific online multiplayer game, namely Overwatch: From the creation of input events, over the network, and back to displaying the results on the local screen. Together they result in the dreaded end-to-end lag, which has a direct impact on the subjective quality one experiences when playing video games. In its investigation, this paper reveals surprising effects in the game's networking behavior that are omitted when colloquially talking about, e.g. a 60 Hz update rate, but must be considered nonetheless. These insights, gained from examining network traces of Overwatch matches that were played on a realistic, resource constrained PC, can then be used to refine end-to-end lag simulation models and reach a better understanding of all responsible lag components.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"268 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133461288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.00038
Mark T. Schmidt, Andreas Stockmayer, Florian Heimgaertner, M. Menth
Hands-on computer networking labs are essential in many computer science curricula. They are conducted either on physical testbeds consisting of PCs, routers, switches, cables, etc., or on fully virtualized testbeds. The latter consist of only virtual machines (VM) that can be interconnected via software configuration. Fully virtualized testbeds require less resources (hardware, space, energy) than physical testbeds but students miss important hands-on experience with networking equipment. In this work, we present a semi-virtualized testbed: students are given physical access to networking interfaces of VMs via patch panels so that they can interconnect them through cables. Similarly to virtualized testbeds, the semi-virtualized testbed requires only little hardware and maintenance effort while preserving the hands-on experience of physical testbeds. We present a Python-based orchestration platform for several virtual student workspaces on a single physical server. Each virtual student workspace contains several VMs acting as clients, servers, and routers that can be configured by students. It is made available to a physical workspace on a 19-inch cabinet consisting of a thin client and patch panels allowing students to physically interconnect their VMs with cables.
{"title":"A Semi-Virtualized Testbed Cluster with a Centralized Server for Networking Education","authors":"Mark T. Schmidt, Andreas Stockmayer, Florian Heimgaertner, M. Menth","doi":"10.1109/ITC30.2018.00038","DOIUrl":"https://doi.org/10.1109/ITC30.2018.00038","url":null,"abstract":"Hands-on computer networking labs are essential in many computer science curricula. They are conducted either on physical testbeds consisting of PCs, routers, switches, cables, etc., or on fully virtualized testbeds. The latter consist of only virtual machines (VM) that can be interconnected via software configuration. Fully virtualized testbeds require less resources (hardware, space, energy) than physical testbeds but students miss important hands-on experience with networking equipment. In this work, we present a semi-virtualized testbed: students are given physical access to networking interfaces of VMs via patch panels so that they can interconnect them through cables. Similarly to virtualized testbeds, the semi-virtualized testbed requires only little hardware and maintenance effort while preserving the hands-on experience of physical testbeds. We present a Python-based orchestration platform for several virtual student workspaces on a single physical server. Each virtual student workspace contains several VMs acting as clients, servers, and routers that can be configured by students. It is made available to a physical workspace on a 19-inch cabinet consisting of a thin client and patch panels allowing students to physically interconnect their VMs with cables.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116165277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ITC30.2018.00015
O. Hohlfeld, Helge Reelfs, Jan Rüth, F. Schmidt, T. Zimmermann, Jens Hiller, Klaus Wehrle
As network speed increases, servers struggle to serve all requests directed at them. This challenge is rooted in a partitioned data path where the split between the kernel space networking stack and user space applications induces overheads. To address this challenge, we propose Santa, an architecture to optimize the data path by enabling server applications to (partially) offload packet processing to a generic rule processor. We exemplify Santa by showing how it can drastically accelerate UDP packet processing in the Linux kernel—a currently neglected domain. Our evaluation focuses on accelerating DNS traffic for which we find a performance increase by a factor of 5.5 on real-world request pattern.
{"title":"Application-Agnostic Offloading of Datagram Processing","authors":"O. Hohlfeld, Helge Reelfs, Jan Rüth, F. Schmidt, T. Zimmermann, Jens Hiller, Klaus Wehrle","doi":"10.1109/ITC30.2018.00015","DOIUrl":"https://doi.org/10.1109/ITC30.2018.00015","url":null,"abstract":"As network speed increases, servers struggle to serve all requests directed at them. This challenge is rooted in a partitioned data path where the split between the kernel space networking stack and user space applications induces overheads. To address this challenge, we propose Santa, an architecture to optimize the data path by enabling server applications to (partially) offload packet processing to a generic rule processor. We exemplify Santa by showing how it can drastically accelerate UDP packet processing in the Linux kernel—a currently neglected domain. Our evaluation focuses on accelerating DNS traffic for which we find a performance increase by a factor of 5.5 on real-world request pattern.","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127910175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/itc30.2018.00007
{"title":"ITC 30 Technical Program Committee Members","authors":"","doi":"10.1109/itc30.2018.00007","DOIUrl":"https://doi.org/10.1109/itc30.2018.00007","url":null,"abstract":"","PeriodicalId":159861,"journal":{"name":"2018 30th International Teletraffic Congress (ITC 30)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131947332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：