Yunsong (Roamer) Lu wrote:
> Theoretically, it's not impossible. *Assuming* it's valuable, TCP can
> pass down this requirement along with other LSO information, Extended
> SOFT LSO can handle it easily before hardware LSO. But, what value do
> you see with such implementation?
This is the problem. For every changes in a protocol,
somehow the LSO may need to be changed to accommodate
that. And how is soft LSO extended? To have a
construct like MDT?
> LSO is not implemented for every single transmission, but for a "stable"
> transmission that doesn't involve PMTU-like "trick", since such rare
> case won't impact performance much. :;
I am not sure what is meant by "stable?" For example,
one common problem using VPN, such as our own punchin,
is PMTU mismatch. So people artificially lower the
interface MTU hoping for the best. When we add this
kind of better PMTUd support to TCP, TCP can adjust the
segment size to detect the correct size to use. It
is a common case.
--
K. Poon.
[EMAIL PROTECTED]
_______________________________________________
networking-discuss mailing list
[email protected]
