Re: [net-next PATCH v4 2/3] net: TCP thin linear timeouts

From: Ilpo Järvinen
Date: Thu Feb 18 2010 - 04:10:00 EST


On Thu, 18 Feb 2010, Franco Fichtner wrote:

> Andreas Petlund wrote:
> > On 02/18/2010 09:41 AM, Ilpo Järvinen wrote:
> >
> > > On Wed, 17 Feb 2010, David Miller wrote:
> > >
> > >
> > > > From: Andreas Petlund <apetlund@xxxxxxxxx>
> > > > Date: Tue, 16 Feb 2010 15:40:41 +0100
> > > >
> > > >
> > > > > @@ -341,6 +342,8 @@ struct tcp_sock {
> > > > > u16 advmss; /* Advertised MSS
> > > > > */
> > > > > u8 frto_counter; /* Number of new acks after RTO */
> > > > > u8 nonagle; /* Disable Nagle algorithm?
> > > > > */
> > > > > + u8 thin_lto : 1,/* Use linear timeouts for thin
> > > > > streams */
> > > > > + thin_undef : 7;
> > > > >
> > > > There is now a gap of 3 unused bytes here in this critical
> > > > core TCP socket data structure.
> > > >
> > > > Please either find a way to avoid this hole, or document
> > > > it with a comment.
> > > >
> > > There would be multiple bits free for use in both frto_counter and nonagle
> > > byte.
> > >
> > >
> >
> > I was playing aroud with this setup:
> >
> > =========
> > u8 nonagle : 4,/* Disable Nagle algorithm? */
> > thin_lto : 1,/* Use linear timeouts for thin streams */
> > thin_dupack : 1,/* Fast retransmit on first dupack */
> > thin_undef : 2;
> > =========
> >
> > Do you think that would do the trick?
> >
>
> According to Ilpo, it would be ok to reduce both ftro_counter and
> nonagle, so why not join all these into u16 and leave the remaining
> free bits documented for other people. Like this:
>
> u16 frto_counter:x; /* Number of new acks after RTO */
> u16 nonagle:y; /* Disable Nagle algorithm? */
> u16 thin_lto:1; /* Use linear timeouts for thin streams */
> u16 unused:15-x-y;
>
> Not sure about the y and x. Ilpo, can you comment on those values?

I don't remember top of the hat how much of nonagle used, but for
frto_counter max value was 3 iirc. However, I'm unsure if compiler is
nowadays wise enough to handle bitfields in some not all so stupid way.
Btw, also in ecn_flags we have some empty space. But all in all that
didn't vacate enough to get 4 bytes so I haven't taken effort of
combining.

--
i.