Date: Mon, 05 Nov 2012 19:58:11 +0200 From: Ian FREISLICH <ianf@cloudseed.co.za> To: Joe Holden <lists@rewt.org.uk> Cc: Davide Italiano <davide@freebsd.org>, Alexander Motin <mav@FreeBSD.org>, FreeBSD Current <freebsd-current@freebsd.org> Subject: Re: Dynamic Ticks/HZ Message-ID: <E1TVQw7-0000SL-Nj@clue.co.za> In-Reply-To: <5097EAC7.1080200@rewt.org.uk> References: <5097EAC7.1080200@rewt.org.uk> <5097E465.3010408@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
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
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E1TVQw7-0000SL-Nj>