From owner-freebsd-current@FreeBSD.ORG Thu Jan 12 22:01:19 2006 Return-Path: X-Original-To: freebsd-current@FreeBSD.org Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A8A8F16A420; Thu, 12 Jan 2006 22:01:19 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 76D7A43D48; Thu, 12 Jan 2006 22:01:15 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.3/8.13.3) with ESMTP id k0CM1D64085751 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 13 Jan 2006 01:01:13 +0300 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.3/8.13.1/Submit) id k0CM1DOc085750; Fri, 13 Jan 2006 01:01:13 +0300 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 13 Jan 2006 01:01:12 +0300 From: Gleb Smirnoff To: Harald Schmalzbauer Message-ID: <20060112220112.GE83922@FreeBSD.org> References: <200601110030.k0B0UPOx009098@repoman.freebsd.org> <200601121847.08044@harrymail> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <200601121847.08044@harrymail> User-Agent: Mutt/1.5.6i Cc: cvs-src@FreeBSD.org, freebsd-current@FreeBSD.org Subject: Re: cvs commit: src/sys/dev/em if_em.c if_em.h X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 12 Jan 2006 22:01:19 -0000 On Thu, Jan 12, 2006 at 06:47:00PM +0100, Harald Schmalzbauer wrote: H> Am Mittwoch, 11. Januar 2006 01:30 CEST schrieb Scott Long: H> > scottl 2006-01-11 00:30:25 UTC H> > H> > FreeBSD src repository H> > H> > Modified files: H> > sys/dev/em if_em.c if_em.h H> > Log: H> > Significant performance improvements for the if_em driver: H> > H> > - Only update the rx ring consumer pointer after running through the H> > rx loop, not with each iteration through the loop. H> > - If possible, use a fast interupt handler instead of an ithread H> > handler. Use the interrupt handler to check and squelch the interrupt, H> > then schedule a taskqueue to do the actual work. This has three H> > benefits: H> H> Thank you very much for your work! Since I'm using many em cards and can't H> get higher tranfer rates compared to fxp (but I wanted to double it so I H> spent some money to replace F-Eth equipment with GbE) I'd like to apply H> your work to RELENG_6. I made the attached diff, but compiler stops here: H> H> /usr/obj/GUNE/usr/src/make.i386/make -V CFILES -V SYSTEM_CFILES -V H> GEN_CFILES | MKDEP_CPP="cc -E" CC="cc" xargs mkdep -a -f .newdep -O2 H> -pipe -fno-strict-aliasing -march=pentium3 -Wall -Wredundant-decls H> -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith H> -Winline -Wcast-qual -fformat-extensions -std=c99 -g -nostdinc -I- -I. H> -I/usr/src/sys -I/usr/src/sys/contrib/altq -I/usr/src/sys/contrib/ipfilter H> -I/usr/src/sys/contrib/pf -I/usr/src/sys/contrib/dev/ath H> -I/usr/src/sys/contrib/dev/ath/freebsd -I/usr/src/sys/contrib/ngatm H> -I/usr/src/sys/dev/twa -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include H> opt_global.h -fno-common -finline-limit=8000 --param H> inline-unit-growth=100 --param large-function-growth=1000 H> -mno-align-long-strings -mpreferred-stack-boundary=2 -mno-mmx -mno-3dnow H> -mno-sse -mno-sse2 -ffreestanding H> /usr/src/sys/dev/em/if_em.c:3178:34: macro "VLAN_INPUT_TAG" requires 4 H> arguments, but only 3 given H> mkdep: compile failed H> *** Error code 1 H> H> Stop in /usr/obj/GUNE/usr/src/sys/CUV-LV. H> *** Error code 1 H> H> I have no idea how to correct this, could you please help me? Or isn't it H> that simple, eg. VLAN isn't the same level in RELENG_6 and -current? I'm going to merge the VLAN_INPUT_TAG() change soon. But merging em(4) requires also a lot of taskqueue code merging. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE