[OpenAFS-devel] .35 sec rx delay bug?

[Derrick Brashear]

On Nov 8, 2007 11:13 AM, chas williams - CONTRACTOR
<chas@cmf.nrl.navy.mil> wrote:
> In message <473281D5.1080100@secure-endpoints.com>,Jeffrey Altman writes:
> >Was this code ever tested?
>
> no idea.  jim had the problem not me.  i run this code locally and i
> havent had any complaints.  i was able to duplicate the issue since
> i have multi-homed servers with two different mtu sizes.
>
> >Does it solve the problem it was intended to solve?
>
> of course.  the solution is not ideal.  as i mentioned, you would need
> path mtu discovery to implement a completely correct solution.  i would
> personally vote that you should not send datagrams > 1500 off your local
> subnet.  while jumbograms increase performance, its not clear to me
> that the benefit outweighs the cost when going outside the local lan.
>
i have pmtu for linux and solaris if you want to try it

> >Or was something else committed in its place?
>
> i believe this was comitted as is as rx-mtu-fixes-20061218.  however,
> i dont closely track what the maintainers of the openafs do.