svn commit: r332770 - in head/sys: conf netinet netinet/tcp_stacks sys

[hiren panchasara]

On 05/01/18 at 05:11P, Warner Losh wrote:
> On Tue, May 1, 2018 at 5:00 PM, Jonathan Looney <jonlooney at gmail.com> wrote:
> 
> > On Mon, Apr 30, 2018 at 3:16 AM, hiren panchasara <
> > hiren at strugglingcoder.info> wrote:
> > >
> > > In my understanding, default stack currently cannot use this mechanism.
> > When do
> > > you think that'll be possible?
> >
> >
> > I think I can speak to Randall's plans for this.

Thank you!
> >
> > Randall chose not to include in this commit the hooks for the default
> > stack to use the high-precision timers. I believe his immediate priorities
> > are upstreaming RACK and BBR. After that, if there is demand, he may
> > upstream the (relatively untested) code that allows the default stack to
> > use the high-precision timers (protected by a non-default kernel option) so
> > others can choose to experiment with it.

I believe it'd be useful to be able to pace packets with the traditional
stack.
> >
> > (By the way, we're hoping to change the terminology away from describing
> > the traditional FreeBSD stack as the "default" stack. In theory, someone
> > can make any stack be their local default. We'll need to figure out what to
> > actually call it at some point. My suggestion was the "FreeBSD" stack,
> > although that is lacking in some imagination. In any case, we should have
> > that discussion at some point in the future.
> >
> 
> Only slightly less poor would be "traditional" stack :)

See, I've already started using this name. :-)

Cheers,
Hiren
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 603 bytes
Desc: not available
URL: <http://lists.freebsd.org/pipermail/svn-src-head/attachments/20180502/22d65bd7/attachment.sig>