It has been a while since I last posted, but thought this one might be of interest to a few of you, especially since I keep running into it every so often.
Some time ago I did a performance analysis of multiple manufacturer NICs. As a part of that test, I also tested the impact of changing the TCP congestion algorithm in VMware from the default New Reno to Cubic. The cubic algorithm consistently delivered better throughput results in the tests, and since then I have updated all of our hosts to use this.
Unfortunately, if the algorithm is set via the VMware 5.5 vCenter Web Interface, not all of the required changes are applied properly to the target ESXi host and upon reboot, the host is unable to connect to vCenter. It took quite a bit of work with VMware until we discovered the root cause. Fortunately, we did identify a simple workaround, documented here: https://communities.vmware.com/thread/506836
For those that hate to go read another document, here is the Cliff Notes version…
If you want to login to the ESXi console, you can run this command:
esxcli network ip netstack set -c cubic -N defaultTcpipStack
For the more adventurous, use the vmware cli and this command and replace <servername> with the host name of choice:
esxcli -s <servername> network ip netstack set -c cubic -N defaultTcpipStack