@nomad dladm show-aggr -p

Add that to gist

Also, did you try on a single ixgbe instead of aggrs? (I wonder if the aggr code trying to find hash values might slow down on v6...)

If I had a cat6 cable I could replicate your experiment but I don't at the moment.

(Also it's release week for SmartOS.)

danmcd, I tried it on a single previously, before I figured out IPv6 was the probable cause. I'll be tearing the aggregate apart next week and trying again.

which fields do you want with that show-aggr? (It insists I have to give -o and arguments.)

or did you want -P or --persistent ?

pastebin.com/74wuHtnj (for dladm show-aggr --persistent)

I wanted -P nomad ==> balancing policy.

But if you're seeing similar degradation on a single link, it's better to run further checks there.

Also, what's the MTU for the link? If it's not 9k (or whatever your ixgbe's max is) already, make it that way and see if the disparity matches or shrinks.

note that there will be a slight degradation in v6 line rate just due to the larger headers. (20 bytes for ipv4 vs 40 for ipv6)

The differenecs he's quoting are way more than the 2% shrinkage on 1500MTU .