From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 18:06:49 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B7E7F410; Mon, 5 Nov 2012 18:06:49 +0000 (UTC) (envelope-from ianf@cloudseed.co.za) Received: from zcs03.jnb1.cloudseed.co.za (zcs03.jnb1.cloudseed.co.za [41.154.0.139]) by mx1.freebsd.org (Postfix) with ESMTP id 457118FC15; Mon, 5 Nov 2012 18:06:48 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by zcs03.jnb1.cloudseed.co.za (Postfix) with ESMTP id 015652B42BB3; Mon, 5 Nov 2012 19:58:15 +0200 (SAST) X-Virus-Scanned: amavisd-new at zcs03.jnb1.cloudseed.co.za Received: from zcs03.jnb1.cloudseed.co.za ([127.0.0.1]) by localhost (zcs03.jnb1.cloudseed.co.za [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 3XNYQZNhbJK9; Mon, 5 Nov 2012 19:58:14 +0200 (SAST) Received: from clue.co.za (unknown [41.154.88.19]) by zcs03.jnb1.cloudseed.co.za (Postfix) with ESMTPSA id 39B7C2B42BAE; Mon, 5 Nov 2012 19:58:14 +0200 (SAST) Received: from localhost ([127.0.0.1] helo=clue.co.za) by clue.co.za with esmtp (Exim 4.80 (FreeBSD)) (envelope-from ) id 1TVQw7-0000SL-Nj; Mon, 05 Nov 2012 19:58:11 +0200 To: Joe Holden From: Ian FREISLICH Subject: Re: Dynamic Ticks/HZ In-Reply-To: <5097EAC7.1080200@rewt.org.uk> References: <5097EAC7.1080200@rewt.org.uk> <5097E465.3010408@FreeBSD.org> X-Attribution: BOFH Date: Mon, 05 Nov 2012 19:58:11 +0200 Message-Id: X-Mailman-Approved-At: Mon, 05 Nov 2012 18:12:04 +0000 Cc: Davide Italiano , Alexander Motin , FreeBSD Current X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 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: Mon, 05 Nov 2012 18:06:49 -0000 Joe Holden wrote: > It looks like the device polling is what was causing it, once I'd > removed that from kernconf it returned to normal - full interupt rate is > ok though if I can increase the rate to a decent level FWIW, this is how my igb(4) system is tuned and with PF, it's able to fill 4xigb interfaces: /boot/loader.conf: # 16 CPUs net.isr.maxthreads="8" net.isr.defaultqlimit="4096" net.isr.maxqlimit="81920" net.isr.direct="1" net.isr.direct_force="1" net.isr.bindthreads="0" kern.ipc.nmbclusters="262144" hw.igb.max_interrupt_rate="32000" hw.igb.rx_process_limit="500" hw.igb.header_split="1" #This setting doesn't seem to work hw.igb.txd="4096" hw.igb.rxd="4096" /etc/sysctl.conf: net.inet.ip.fastforwarding=1 kern.random.sys.harvest.interrupt=0 kern.random.sys.harvest.ethernet=0 kern.random.sys.harvest.point_to_point=0 Ian -- Ian Freislich