Re: [tcpm] PLPMTUD for all protocols

[Tom Jones <[e-mail]>]

On Wed, Mar 28, 2018 at 10:43:40AM +0200, Mikael Abrahamsson wrote:
> 
> Hi,
> 
> In trying to advocate for all protocols implementing PLPMTUD (RFC4821) and 
> shipping with it default on, I received pushback when I suggested/asked 
> why modern TCP stacks don't come with PMTU blackhole detect turned on.
> 
> Relevant reading is draft-bonica-intarea-frag-fragile-01, where PMTU 
> blackhole is one part of this problem space.
> 
> I tried turning on PMTU blackhole in Linux quickly in a case I had, and it 
> worked around the PMTU blackhole we had for a certain deployment scenario 
> (which couldn't be fixed unless the NMS could reconfigure the device in 
> question, which it couldn't because PMTU blackhole existed).
> 
> People suggested to me that the current TCP stack implementations are 
> broken when it comes to PMTU blackhole detection and workaround, so that's 
> why it's not on.
> 
> What's wrong with it, and how do we fix it?


Related discussion on the freebsd-net mailing list.
https://lists.freebsd.org/pipermail/freebsd-net/2018-March/049916.html

As I understand there are issues with FreeBSD increasing again after
detecting a blackhole. There is not currently enough state kept to
regrow the mtu. 

- [tj]