Re: RFC: TSO patch for current

On 9/5/06, Andre Oppermann <andre_at_freebsd.org> wrote:
> Jack Vogel wrote:
> > On 9/5/06, Andre Oppermann <andre_at_freebsd.org> wrote:
> >> Prafulla Deuskar wrote:
> >> > Your patch looks good and is the way to go.
> >> >
> >> > So after Jack confirms that your patch works with the em driver
> >> > would you commit to to -current?
> >>
> >> Absolutely.  :-)
> >>
> >> > The driver related changes can follow..
> >> >
> >> > Later we also need to fix ifconfig so that user can enable/disable
> >> TSO on the interface.
> >>
> >> I'll do that together with the TSO code.
> >
> > OK, I've built and done some touch testing of this. I like it, the
> > driver has
> > some counters of the number of TSO bursts it does, and I think I see more
> > per netperf test with your patch than mine.
> >
> > Hard to do real performance testing with all that WITNESS stuff in, but
> > I will be making a 6.1 version of your patch to test with since I have my
> > driver running on that anyway.
>
> You can disable WITNESS and INVARIANTS pretty easily in -current and
> get the full performance with it.

Last time I tried that I think the kernel wouldnt build, but that was
like 6 months ago, so I just kicked off a build with this stuff off, and
we'll see how it looks :)

> > If you do the ifconfig changes there will need to be a small amount of
> > code added to em_ioctl() but it should be trivial.
> >
> > You want me to reissue a driver patch with changes for your code?
>
> Yes, please do so.  I've got a dual-em card which I can test with myself.

OK, attached new patch, this one even has the ioctl change so when
you get the ifconfig change in it will be ready.

Cheers,

Jack