Date: Mon, 10 Sep 2001 15:35:45 -0500 From: Alfred Perlstein <bright@mu.org> To: Charles Randall <crandall@matchlogic.com> Cc: 'Jonathan Lemon' <jlemon@flugsvamp.com>, Julian Elischer <julian@elischer.org>, kent@erix.ericsson.se, hackers@freebsd.org Subject: Re: How to force small TCP packets? Message-ID: <20010910153545.T2965@elvis.mu.org> In-Reply-To: <5FE9B713CCCDD311A03400508B8B30130828F421@bdr-xcln.corp.matchlogic.com>; from crandall@matchlogic.com on Mon, Sep 10, 2001 at 02:31:57PM -0600 References: <5FE9B713CCCDD311A03400508B8B30130828F421@bdr-xcln.corp.matchlogic.com>
next in thread | previous in thread | raw e-mail | index | archive | help
(re: testing a client to see if it deals with short messages over a socket) * Charles Randall <crandall@matchlogic.com> [010910 15:32] wrote: > Out of curiosity, can ipfw+dummynet do something like this? I've already responded to the poster in private about it because my initial suggestion was wrong (i hadn't read his email thouroughly enough). One way that should work without having to do anything tricky is using setsockopt with SO_RCVBUF to lower the buffer space, this should force the remote side to buffer and reduce the amount of data to be read. I'm still unsure if this is appropriate because the kernel may silently (or loudly) complain about a SO_RCVBUF that appears to be too small. You may be able to also do this by setting the sysctl kern.ipc.maxsockbuf to something small. -- -Alfred Perlstein [alfred@freebsd.org] 'Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom.' To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010910153545.T2965>