Date: Sun, 21 Nov 2004 09:27:29 -0800 From: Sean McNeil <sean@mcneil.com> To: Shunsuke SHINOMIYA <shino@fornext.org> Cc: Jeremie Le Hen <jeremie@le-hen.org> Subject: Re: Re[2]: serious networking (em) performance (ggate and NFS) problem Message-ID: <1101058049.12022.5.camel@server.mcneil.com> In-Reply-To: <20041121205158.45CE.SHINO@fornext.org> References: <20041119185315.C43D.SHINO@fornext.org> <20041119120102.GM69710@obiwan.tataz.chchile.org> <20041121205158.45CE.SHINO@fornext.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--=-+MwiF7b73TDd4FXZ8OfL Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Sun, 2004-11-21 at 21:27 +0900, Shunsuke SHINOMIYA wrote: > Jeremie, thank you for your comment. >=20 > I did simple benchmark at some settings. >=20 > I used two boxes which are single Xeon 2.4GHz with on-boarded em. > I measured a TCP throughput by iperf. >=20 > These results show that the throughput of TCP increased if Interrupt > Moderation is turned OFF. At least, adjusting these parameters affected > TCP performance. Other appropriate combination of parameter may exist. I have found interrupt moderation to seriously kill gigE performance. Another test you can make is to have the driver always defrag packets in em_encap(). Something like m_head =3D m_defrag(*m_headp, M_DONTWAIT); if (m_head =3D=3D NULL) return ENOBUFS; --=-+MwiF7b73TDd4FXZ8OfL Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.6 (FreeBSD) iD8DBQBBoNAByQsGN30uGE4RAhSXAKDEgYADxq+/EmcCYap8FGRlCgI8/ACeLxz/ w7l/SkoYwwZfQMVn4w/KTpI= =CGLu -----END PGP SIGNATURE----- --=-+MwiF7b73TDd4FXZ8OfL--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1101058049.12022.5.camel>