Sharing state between host and upstream network: LACP part 3
So far in the previous articles, we’ve covered the initial objections to LACP a deep dive on the effect on traffic patterns in an MLAG environment without LACP/Static-LAG. In this article we’ll explore how LACP differs from all other available teaming techniques and then also show how it could’ve solved a problem in this particular deployment.
I originally set out to write this as a single article, but to explain the nuances it quickly spiraled beyond that. So I decided to split it up into a few parts.
• Part1: Design choices – Which NIC teaming mode to select
• Part2: How MLAG interacts with the host
• Part3: “Ships in the night” – Sharing state between host and upstream network
Ships in the night
An important element to consider is LACP is the only uplink protocol supported by VMware that directly exchanges any network state information between the host and its upstream switches. An ESXi host is also sortof a host, but also sortof a network switch (in so far as it does forward packets locally and makes path decisions for north/south traffic); here in lies the problem, we effectively have network devices forwarding packets between each other, but Continue reading


OpenStack is not dead, but 'containers are sexy.'
Ericsson also has a 5G/motor vehicle consortium based in Germany.
'The time has come to standardize on a common interface,' says CNCF.
The typical size of an OpenStack cloud increased, says survey.
Multiple vendors will use the test sites at the same time.
Ixia collaborates with CORD Project; IBM releases new developer capabilities on Bluemix.

