overview to build a virtualized network topology from the most base elements it’s as simple as starting a virtual machine with the necessary number of virtualized interfaces and interconnecting these virtual interfaces to other virtual machines or physical interfaces. while there are tools1 which will nicely automate the creation of topologies and handle the lifecycle of VMs. all of these are effectively placing a nice wrapper around the following process....
it looks like the fact that folks pass communities around like the common cold is a bulb that is starting to light. oft discussed over beers, but little research in this space. here’s a first run at this research. must read paper: BGP communities: even more worms in the routing can update (20190323) it looks like one of the authors has written a few blog posts on the topic as well for the RIPE folks....
items dislodged from my reading queue of particular interest. first off - if you don’t have the morning paper in your RSS reader, you should. nerd bits slacker: fast distribution with lazy docker containers what happens behind the scenes when you type docker run. i’ve scratched my head aplenty over the operation of AUFS and the complementary machinery around docker volumes. lots of dots get connected here. borg, omega, and kubernetes the most recent ACM queue article from the borg crew re: container scheduling at the GOOG....
application layer multicast from stuff the internet says on scalability … ...
abstract The industry is in the mood for programmable networks, where an operator can dynamically deploy network functions on network devices, akin to how one deploys virtual machines on physical machines in a cloud environment. Such flexibility brings along the threat of unpredictable behavior and performance. What are the minimum restrictions that we need to impose on network functionality such that we are able to verify that a network device behaves and performs as expected, for example, does not crash or enter an infinite loop?...