From owner-freebsd-net Tue Feb 13 18:36:20 2001 Delivered-To: freebsd-net@freebsd.org Received: from iguana.aciri.org (iguana.aciri.org [192.150.187.36]) by hub.freebsd.org (Postfix) with ESMTP id 9B55E37B503 for ; Tue, 13 Feb 2001 18:36:18 -0800 (PST) Received: (from rizzo@localhost) by iguana.aciri.org (8.11.1/8.11.1) id f1E2aCU57546; Tue, 13 Feb 2001 18:36:12 -0800 (PST) (envelope-from rizzo) From: Luigi Rizzo Message-Id: <200102140236.f1E2aCU57546@iguana.aciri.org> Subject: Re: fxp performance ? In-Reply-To: <20010214112310G.kjc@csl.sony.co.jp> from Kenjiro Cho at "Feb 14, 2001 11:23:10 am" To: kjc@csl.sony.co.jp (Kenjiro Cho) Date: Tue, 13 Feb 2001 18:36:07 -0800 (PST) Cc: rizzo@aciri.org, net@freebsd.org X-Mailer: ELM [version 2.4ME+ PL43 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > Unfortunately my diagnostic tools do not let me see what is going > > on on the wire, whether the spacing is larger than it should be, actually i managed to instrument the driver and the spacing between interrupts (with a change similar to the one you proposed -- i make them occur every N packets ) is approx (N*9)us which seems to suggest a larger spacing than it should be. Wonder if the interframe spacing or the preamble lenght is incorrect... cheers luigi > > It might be related to the fact that the fxp driver doesn't generate > a transmission complete interrupt unless the interface queue length is > exactly 119. > > Does the following change make any difference? > > --- if_fxp.c- Wed Feb 14 11:13:42 2001 > +++ if_fxp.c Wed Feb 14 11:14:27 2001 > @@ -1183,6 +1183,7 @@ > * going again if suspended. > */ > if (txp != NULL) { > + txp->cb_command |= FXP_CB_COMMAND_I; > fxp_scb_wait(sc); > CSR_WRITE_1(sc, FXP_CSR_SCB_COMMAND, FXP_SCB_COMMAND_CU_RESUME); > } > > -Kenjiro > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message