|7:30-4:00PM||Registration / Breakfast|
|8:00-8:30AM||CHI-NOG 05 Overview [Video]
Opening remarks, introduction to the conference, overview and CHI-NOG’s roadmap.
|8:30-9:00AM||Designing and Experimenting with Datacenter Architecture [Video]
In recent years, we have seen several proposals for data center interconnects that each optimize for different objectives. In this talk, I will put these research results in perspectives as well as talk about systems we are building to aid in at-scale experimental evaluation of such proposals.This talk has two parts. In the first part, we propose an approach to the design of large-scale general-purpose data center networks based on the notions of volume and area universality introduced in the 1980’s in the context of VLSI design. We suggest that the principle goal of the network designer should be to build a single network that is provably competitive, for any application, with any network that can be built for the same amount of money. After describing our approach, we survey the technology choices available to network designers today, and examine several existing commercial data center networks. In the most recent of these networks resources are allocated roughly as we suggest in our work.In the second part of the talk, I will describe CloudLab, a facility we are building to study disruptive technologies on the data center networking and cloud computing fronts. With CloudLab researchers have access to “bare metal clouds”, where they can control or change several low level aspects, as well as perform deep instrumentation. Thus, CloudLab facilitates repeatable experiments on foundational ideas and technologies in cloud computing.
|by Aditya Akella|
|9:00-9:30AM||Creating a Self Aware Network Device [Video]
By extending scripting to the network device it is possible to have the device proactively adjust or troubleshoot itself. The presentation will demonstrate some proof of concept code to proactively troubleshoot BGP, dynamically adjust CoPP and provide ACL accounting.
|by Pete Lumbis|
|9:30-10:00AM||How Traceroute Explains the Internet [Video]
Perhaps only after Ping, traceroute is often the most common and widely used tool in a variety of network troubleshooting or discovery operations. Like so many Internet applications, traceroute was an afterthought, but has become an indispensable part of our toolbox. Most newcomers view it as a relatively simple tool that helps identify the path, or a path, between two hosts. However, when we look more closely, not only can traceroute tell us so much more, it can do much more. In this talk we examine the versatility of this quintessential little piece of software and how it explains so much more about how the Internet works than we may have ever thought.
|by John Kristoff|
|10:15-10:45AM||DDoS Mitigation using BGP FlowSpec [Video]
The BGP Flow Specification defined in RFC 5575 gives network operators an additional tool to mitigate the effects of DDoS attacks on their network. In this talk, we will look at the previous tools available to operators for blocking DDoS attacks. We will then look at how BGP Flowspec aims to improve upon those methods. Finally, we will take a look at where BGP Flowspec is working and what needs to be improved to make this tool even more effective.
|by Justin Ryburn|
|10:45-11:15AM||Middle-Out Automation Automating an IXP [Video]
The presentation will go over a use case of automating IXPs by looking at the United IX Chicago. Matt will discuss how he started with open source project IXP Manager and it’s database then took it to the next level with PeeringDB 2.0 integration, switch port and ACL provisioning, and real time blackholing across the peering fabric.
|by Matt Griswold|
|11:15-11:45AM|| The Handmade Internet [Video]
Andrew Blum has been exploring the physical infrastructure of the Internet since 2008, writing in his book “Tubes: A Journey to the Center of the Internet” about who he met there, and what he saw. In this presentation he’ll share stories from those travels, before focusing his attention closer to home, on the world’s largest data center campus: 350 East Cermak, here in Chicago. He’s recently produced a new film that takes an unusual look at the heart of this building. Andrew will debut the new film, and he’ll highlight points from his book, Tubes (which will also be handed out to participants).
|by Andrew Blum|
|11:45-1:00 PM||Lunch (Lake Room)|
|1:00-1:30PM||Secure Layer 3 SDX Concept Interdomain SDN [Video]
Present a model for making practical use of BGP routes verified against RPKI and utilizing BGP FlowSpec to generate flowmods for prefixes within a software defined exchange point as a modular mechanism for building a secure SDX with any flexible SDN controller.
|by Nick Buraglio|
|1:30-2:00PM||Midwest Peering Panel [Video]
The panel will discuss the Midwest IXPs. Role of the region in the national Internet infrastructure.
|Moderated by Tom Kacprzynski, including
-Mark Cooper (AMS-IX Chicago)
-Matt Griswold (United-IX)
-Justin Wilson (MidWest-IX)
-David Farmer (MICE)
|2:00-2:30PM||Anatomy of a Multi-Vector DDoS Attack [Video]
Attackers are becoming increasingly sophisticated and they are leveraging multiple attack mechanisms and vectors to distract and then disrupt or exfiltrate data. The presentation will walk the audience through an attack and the mechanisms used to both visualize and protect. Why is this relevant? As indicated earlier the nature of attacks are changing and becoming more frequent. They are being used for things other than taking out down servers, firewalls etc. Sometimes and more often than not they are being used as a smoke screen to hide the true nature of the attack. Worse case scenario they are becoming business impacting. There is a real need to understand and the ability to rapidly decode the attack, understand its real reason and outline techniques, some automated to stop this rapidly evolving threat.
|by Bipin Mistry|
|2:45-3:15PM||Funding Innovative Network and Cybersecurity Research [Video]
The National Science Foundation (NSF) funds breakthrough research in all fields of science and engineering. In order to enable such discovery, NSF provides support for High Performance Computing facilities, networked scientific equipment, scientific software and high speed, global networking. NSF has enabled campuses and national labs to push the boundaries of networking by encouraging development and deployment of 100Gb networking with high speed, Intrusion Detection capabilities and secure Software Defined Networking (SDN).
|by Anita Nikolich|
|3:15-3:45PM||Optimizing Your Virtual Switch for VXLAN [Video]
In this session we’ll discuss the considerations that should be taken into account to optimize software switching inside a VMware vSphere hypervisor. We’ll touch on VXLAN frame format, how and why hardware offload works, configuration of NIC based offload and show supporting test results to support the topic.
|by Ron Fuller|
|3:45-4:15PM||Pushing Light to the Edges and Why It Probably Doesn’t Matter [Video]
The financial industry has driven a technology war to reduce networking latency to infinitesimal levels. We will discuss how this driver has pushed light to the edges of the network, as well as to the edge of physics. Based on more than a decade of experiences involved as a ground soldier and strategic planner in these battles, I will talk about some of the more extreme latency reducing techniques and the drivers of those techniques. I will describe a sample company’s effort to employ many of these techniques to maximize their profit by employing a latency optimized wavelength circuit switched passive optical network with some other tricks. Finally, I will break down why this is probably not a war worth fighting. I will explain why in most cases it’s no longer the right way to fight the battle.
|by Brian Martin|
|4:15-4:45PM||VXLAN Routing Design [Video]
When and where should you route VXLAN traffic? We’ll discuss VXLAN bridging and routing design considerations, along with use cases for multi-tenant, enterprise, and DCI deployments.
|by Darrin Machay|
|5:00-8:00PM||Social Event (Great Room) & Dinner [Highlights Video]
Come to the after party to meet all attendees and speakers while enjoying our 3 hour open bar.