Date: Thu, 16 Feb 2006 21:45:07 +0000 From: David Malone <dwmalone@maths.tcd.ie> To: freebsd-stable@freebsd.org Subject: Re: tcp throughput and net.inet.tcp.inflight.enable Message-ID: <20060216214507.GA91928@walton.maths.tcd.ie> In-Reply-To: <20060216121604.GE55530@e-Gitt.NET> References: <6.2.3.4.0.20060215221957.076524f8@64.7.153.2> <20060216100359.GA10327@jbell.maths.tcd.ie> <20060216121604.GE55530@e-Gitt.NET>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Feb 16, 2006 at 01:16:04PM +0100, Oliver Brandmueller wrote:
> Maybe it's an idea to make this an per-interface value. On my local GigE
> NFS network it might not be useful (well, maybe even lowering the
> performance), while on another interface with lots of connects from all
> over the world does a good job.
Andre has just committed something which disables this on TCP
conections with a short round trip time - this is probably quite
a good workaround for now:
http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/netinet/tcp_subr.c?#rev1.237
David.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060216214507.GA91928>