Comment: | Some changes suggested by Axel Neumann.
- Rewording of intro to challenges slide (also reversed title). - Indicate interesting features of OpenWrt. - Mention root access to containers. - LXC is used to manage containers. - Change title of experiments slide. - Indicate minimum layer available to experiments. - Mention IEEE P2P'12 demos. - Indicate that DLEP and API experiments don't require slices. - Also, API experiments will soon be supported, but not yet. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA1: |
a413d4ac9afead45660c5d7fbea71c42 |
User & Date: | ivan on 2012-09-25 22:02:39 |
Other Links: | manifest | tags |
2012-09-26
| ||
08:10 | More correct definition of gateways as entry points to mgmt net. check-in: b44e59136a user: ivan tags: trunk | |
2012-09-25
| ||
22:02 |
Some changes suggested by Axel Neumann.
- Rewording of intro to challenges slide (also reversed title). - Indicate interesting features of OpenWrt. - Mention root access to containers. - LXC is used to manage containers. - Change title of experiments slide. - Indicate minimum layer available to experiments. - Mention IEEE P2P'12 demos. - Indicate that DLEP and API experiments don't require slices. - Also, API experiments will soon be supported, but not yet. check-in: a413d4ac9a user: ivan tags: trunk | |
19:16 | Put all challenges as "testbed requirement vs. CN characteristic/requirement". check-in: 542baf991d user: ivan tags: trunk | |
Modified script.txt from [2552d02c56] to [adbf65b445].
38 38 # Node maps here for CNs with captures from node DBs. 39 39 - Integrates and extends three community networks: guifi.net, FunkFeuer, AWMN. 40 40 - Also includes nodes in participating research centres. 41 41 - All linked together over the FEDERICA research backbone. 42 42 - All its software and documentation is “free as in freedom”, anyone can setup 43 43 a CONFINE testbed like Community-Lab. 44 44 45 -* Challenges and requirements 46 -CNs pose unique challenges for a testbed. How to 45 +* Requirements and challenges 46 +A testbed has requirements that are challenged by the unique characteristics 47 +of CNs. For instance, how to 47 48 48 49 ** Simple management vs. Distributed node ownership 49 50 - manage devices belonging to diverse owners? 50 51 51 52 ** Features vs. Lightweight, low cost 52 53 - support devices ranging from PCs to embedded boards? 53 54 ................................................................................ 116 117 - Completely normal CN device, so existing ones can be used. 117 118 - Routes traffic between the CN and the node's wired local network (which 118 119 runs no routing protocol). 119 120 - The research device 120 121 - Usually more powerful than CD, since experiments run here. 121 122 - A separated RD minimizes tampering with CN infrastructure. 122 123 - Also experiments can't crash the CD. 123 - - Runs OpenWrt firmware customized by CONFINE. 124 + - Runs the versatile, light and free OpenWrt distro, customized by CONFINE. 124 125 - Slivers are implemented as lightweight Linux containers. 125 - - Provide a familiar and flexible env for researchers. 126 + - So researchers get root access to a familiar environment. 126 127 - Direct interfaces allow low-level interaction of experiments with the CN 127 128 bypassing the CD. 128 129 - Control software 129 - - Uses LXC tools on containers to enforce resource limitation, resource 130 + - Uses LXC tools to manage containers and enforce resource limits, 130 131 isolation and node stability. 131 132 - Uses traffic control, filtering and anonymization to ensure network 132 133 stability, isolation and privacy (partialy implemented). 133 134 - The recovery device (not implemented) can force a remote hardware reboot of 134 135 the RD in case it hangs. It also helps with upgrade and recovery. 135 136 136 -* Supported experiments 137 +* Experiments support 137 138 # Node simplified diagram, hover to interesting parts. 138 139 Researchers can configure slivers with different types of network interfaces 139 140 depending on the connectivity needs of experiments. For instance, to 140 141 141 -- mimic a home PC: use the private interface, which has traffic forwarded 142 +- mimic a home PC: use the private interface, which has L3 traffic forwarded 142 143 using NAT to the CN but filtered to ensure network stability. 143 144 - implement a network service: create a public interface, which has a CN 144 - address and traffic routed directly to the CN but filtered to ensure network 145 - stability. 145 + address and L3 traffic routed directly to the CN but filtered to ensure 146 + network stability. 146 147 - experiment with routing algorithms: create an isolated interface, which uses 147 - a VLAN on top of a direct interface. All traffic is allowed, but only 148 + a VLAN on top of a direct interface. All L2 traffic is allowed, but only 148 149 between other slivers of the same slice with isolated interfaces on the same 149 150 physical link. 150 151 151 -Not yet implemented: 152 +These were demonstrated with BitTorrent and mesh routing experiments at IEEE 153 +P2P'12 Conference. Future support is planned for experiments that: 152 154 153 155 - analyze traffic: create a passive interface to capture traffic on a direct 154 156 interface, which is filtered and anonymized to ensure network privacy. 155 157 - perform low-level testing: the sliver is given free raw access to a direct 156 158 interface. For privacy, isolation and stability reasons this should only be 157 159 allowed in exceptional occasions. 158 160 159 -RDs will soon be able to provide link quality and bandwidth usage measurements 160 -for all their interfaces through the DLEP protocol. 161 +# List example experiments, add these. 162 +Besides experiments run in slices, researchers will soon be able to collect 163 +link quality and bandwidth usage measurements of all RDs' interfaces through 164 +the DLEP protocol. 161 165 162 -Finally, the server and nodes publish management information through an API 163 -that can be used to study the testbed itself, or to implement external 164 -services like node monitoring and selection. 166 +Moreover, the server and nodes will soon publish management information 167 +through an API that would be used to study the testbed itself, or to implement 168 +external services like node monitoring and selection. 165 169 166 170 ** An example experiment 167 171 # Event diagram, hover over components explained. 168 172 To show how the testbed works: two slivers which ping each other. 169 173 170 174 1. The researcher first contacts the server and registers a slice description 171 175 which specifies a template for slivers (e.g. Debian Squeeze) and includes
Modified slides.svg from [0e2fe8a887] to [f13c92b71a].
cannot compute difference between binary files