acruhl@gmail.com wrote:

> > You are right: I get similar results with a generic kernel on my
> > qube2, no performance decrease if your gt.c patch is activated.
> >
> > The general decrease of network performance in my formerly reported
> > results seem to be related to the activated pf (especially due to
> > scrub rules).
 :
> My performance data is similar enough to be called the same. Sorry I
> didn't take the time to capture it all.

Okay, thank you for your reports.

> Is this only going to -current?

cobalt/dev/gt.c changes can be pulled up to netbsd-3 easily,
but changes against ICU part (which might effects devices
on Qube2's PCI slot) in my patch may be problematic.

If there is popular demand to pullup the latter part,
I'll consider how I can proceed it to make pullups easier.
---
Izumi Tsutsui