From mboxrd@z Thu Jan 1 00:00:00 1970 From: Olaf Kirch Subject: Re: [RFC] TCP congestion schedulers Date: Tue, 22 Mar 2005 02:41:54 +0100 Message-ID: <20050322014154.GB4555@suse.de> References: <20050225120814.5fa77b13@dxpl.pdx.osdl.net> <20050309210442.3e9786a6.davem@davemloft.net> <4230288F.1030202@ev-en.org> <20050310182629.1eab09ec.davem@davemloft.net> <20050311120054.4bbf675a@dxpl.pdx.osdl.net> <20050311201011.360c00da.davem@davemloft.net> <20050314151726.532af90d@dxpl.pdx.osdl.net> <423F627C.2060100@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@oss.sgi.com To: Rick Jones Content-Disposition: inline In-Reply-To: <423F627C.2060100@hp.com> Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Mon, Mar 21, 2005 at 04:10:36PM -0800, Rick Jones wrote: > I would put-forth netperf - but then I'm of course biased. It is I think that was one of the benchmarks where the ia64 slowdown with LSM was diagnosed; netperf suffered some 10-15% degradation. And that was just with the capability module loaded, no fancy stuff going on. After we hacked up LSM to inline the capability checks in the default case, performance was back to normal. We didn't bother to pin-point where the loss actually occured, but my suspicion is the major offender was the per-skb check. Olaf -- Olaf Kirch | --- o --- Nous sommes du soleil we love when we play okir@suse.de | / | \ sol.dhoop.naytheet.ah kin.ir.samse.qurax