Date: Wed, 18 Jul 2012 18:41:00 +0400 From: "Alexander V. Chernikov" <melifaro@FreeBSD.org> To: Eugene Grosbein <egrosbein@rdtc.ru> Cc: Konstantin Belousov <kostikbel@gmail.com>, Doug Barton <dougb@freebsd.org>, Luigi Rizzo <rizzo@iet.unipi.it>, net@freebsd.org Subject: Re: FreeBSD 10G forwarding performance @Intel Message-ID: <5006CAFC.1000206@FreeBSD.org> In-Reply-To: <500566F3.9050101@rdtc.ru> References: <4FF36438.2030902@FreeBSD.org> <4FF3E2C4.7050701@FreeBSD.org> <4FF3FB14.8020006@FreeBSD.org> <4FF402D1.4000505@FreeBSD.org> <20120704091241.GA99164@onelab2.iet.unipi.it> <4FF412B9.3000406@FreeBSD.org> <20120704154856.GC3680@onelab2.iet.unipi.it> <4FF59955.5090406@FreeBSD.org> <20120706061126.GA65432@onelab2.iet.unipi.it> <500452A5.3070501@FreeBSD.org> <20120716232352.GE2676@deviant.kiev.zoral.com.ua> <500566F3.9050101@rdtc.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
On 17.07.2012 17:21, Eugene Grosbein wrote: > 17.07.2012 06:23, Konstantin Belousov пишет: > >> I do not think that your 'per-cpu' counter are correct. The thread >> migration or rescheduling causes the fetch or update of the wrong >> per-cpu structure. This allows parallel updates with undefined >> consequences. > >> From practical point of view, I'like to state that most of us do NOT > need scientifically exact ipfw counters values when pushing hardware to its maximum. > > Personaly, I'd like to have tunable that gives me another 15% of speed > at cost of bad ipfw counters I don't use anyway. It seems that this can be done even with sysctl. The same approach can be applied to per-cpu interface counters (and global per-protocol statistics). > > Eugene Grosbein > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > -- WBR, Alexander
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5006CAFC.1000206>