Re: [tcpm] I-D Action: draft-nishida-tcpm-agg-syn-ext-00.txt

Hi everyone,

maybe I can add to the measurements that Matthew cited.
We performed these only once. But we are doing other measurements that we do more frequently.

From these I can report further numbers that we never got around to actually publish.

We look for TFO support on port 80 and we send TFO cookie requests to all of IPv4.
We get roughly 3.2M valid replies with TFO cookies (as of late 2019), which rose from 500k (mid 2017).

Regarding the mirrored options, we see around 70k - 80k empty cookie replies (essentially, we get our cookie request back) that have the same behavior as outlined in Olivier’s blogpost, this number is rather stable, sometimes 10k more or less.
This behavior is focussed on IPs residing in Chinese autonomous systems.
Our assumption has always been that this mirroring is performed by some middlebox and not an end-host.

If there is interest, I can perform these measurements with an unassigned TCP option number.

Best
 Jan

> On 8. Feb 2021, at 23:15, Matthew Luckie <mjl@caida.org> wrote:
> 
> Hi Richard,
> 
> On Mon, Feb 08, 2021 at 10:46:45PM +0100, Scheffenegger, Richard wrote:
>> Hi Yoshi,
>> 
>> Sorry to nitpick - in your draft, you mention that some hosts reflect
>> back unknown tcp options, which is why you are using different GID
>> mappings between SYN and SYN,ACK.
>> 
>> I did read about this behavior concerning TCP header flags / reserved
>> bits - but have not come across a paper where this behavior is described
>> for unknown TCP options (or I may have missed that aspect in the various
>> studies around TCP option investigations done by MPTCP and other groups).
> 
> There is some discussion of systems that seem to reflect TCP options here:
> 
> http://blog.multipath-tcp.org/blog/html/2018/12/19/which_servers_use_multipath_tcp.html
> 
> Matthew_______________________________________________
> tcpm mailing list
> tcpm@ietf.org
> https://www.ietf.org/mailman/listinfo/tcpm