Date: Sat, 5 Feb 2005 01:53:54 +0200 From: Ruslan Ermilov <ru@freebsd.org> To: Guy Helmer <ghelmer@palisadesys.com> Cc: freebsd-net@freebsd.org Subject: Re: Netgraph performance question Message-ID: <20050204235354.GB95344@ip.net.ua> In-Reply-To: <4203EC87.3070504@palisadesys.com> References: <4203AAE3.4090906@palisadesys.com> <20050204204804.GC71363@ip.net.ua> <4203EC87.3070504@palisadesys.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--oC1+HKm2/end4ao3 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Feb 04, 2005 at 03:43:35PM -0600, Guy Helmer wrote: >=20 > I'm sorry, I mis-wrote. My ng_tee is actually modified to only passes > packets to the r2l/l2r hooks if they are connected, otherwise packets = are > passed directly to the left/right hooks (so it's an optional divert), = so > there is no m_dup anymore in my modified ng_tee. >=20 > I assumed that the bridging and trip through userland would only add > latency to the connection, but the result of the performance test seem= ed > to indicate that there is either a bottleneck I need to solve or my > testing methodology was flawed. >=20 If you pass packets through userland, then it is even more performance penalty, as it involves userspace<->kernel copying, twice for each packet. Cheers, --=20 Ruslan Ermilov ru@FreeBSD.org FreeBSD committer --oC1+HKm2/end4ao3 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.6 (FreeBSD) iD8DBQFCBAsSqRfpzJluFF4RAqcOAJ92ljJSEZuaCfl/8ctSiwHDYPtSjwCfR2iy LcGhfyrptuZdWkskbonwoDo= =YWuj -----END PGP SIGNATURE----- --oC1+HKm2/end4ao3--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050204235354.GB95344>