On Thu, 09 Mar 2006 15:06:22 -0800 (PST) "David S. Miller" <[EMAIL PROTECTED]> wrote:
> From: Stephen Hemminger <[EMAIL PROTECTED]> > Date: Thu, 9 Mar 2006 14:56:43 -0800 > > > This patch is changes the initial TCP congestion window for connections that > > are over the loopback device. This gives better for performance for > > applications > > that do lots of small writes. It might also help for idiotic benchmarks. > > > > See: http://bugzilla.kernel.org/show_bug.cgi?id=6177 > > > > Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]> > > If we have a TC or netfilter rule that rewrites the destination > this change is wrong. Then the dst would get changed, no breakage. > Stop this insane crap, and fix JAVA already. Stop doing this garbage > in the kernel to work around it. Each suggestion I'm seeing gets > worse and worse. Like Sun is going to give me the source?... > You cannot disable Nagle via sockopt(), do small writes, and expect > good performance. That is the end of the story. It should really be corking. > I'm really pissed off that this horrible workaround binge for Java > continues, it's in the worst taste possible, it's wrong, and I'm never > going to accept such a horrible patch. You're usually much better > about these kinds of things Stephen, please stop this. I disagree, it is no worse than the existing optimizations for loopack which also leave a bad taste in my mouth. I didn't say you had to take it, just what and where such a change would be. - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
