Date: Sun, 24 Jun 2001 22:44:13 -0500 (CDT) From: Mike Silbersack <silby@silby.com> To: Alfred Perlstein <bright@sneakerz.org> Cc: Mike Silbersack <silby@FreeBSD.org>, <cvs-committers@FreeBSD.org>, <cvs-all@FreeBSD.org>, <jlemon@freebsd.org>, <bmilekic@freebsd.org> Subject: Re: cvs commit: src/sys/netinet tcp_input.c tcp_output.c tcp_subr.c tcp_timer.c tcp_usrreq.c tcp_var.h Message-ID: <20010624223750.Y1104-100000@achilles.silby.com> In-Reply-To: <20010623102801.F57058@sneakerz.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, 23 Jun 2001, Alfred Perlstein wrote: > > Eliminate the allocation of a tcp template structure for each > > connection. The information contained in a tcptemp can be > > reconstructed from a tcpcb when needed. > > I may have missed it, but did you guys happen to run a perf test > on this along the same lines as the excellent work done to benchmark > the new mbuf allocator? I did runs of netperf -l 30 with all three cases (old, after my commit, after jlemon's commit), and there's no statistically observeable difference in performance. No big surprise there, the memory copies / zeros of the headers are probably dwarfed by the time spent copying the data. I suppose that the results would turn out differently on a heavily loaded system with thousands of mbufs allocated across hundreds of pages. I suspect that the new scheme w/o tcp templates would start to show improvements as the mbuf usage increased. But in any case, the decreased mbuf usage seems quite nice, and was the major motivation for the patch. Mike "Silby" Silbersack To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010624223750.Y1104-100000>