From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dipankar Sarma Subject: Re: route cache DoS testing and softirqs Date: Wed, 31 Mar 2004 22:40:24 +0530 Sender: netdev-bounce@oss.sgi.com Message-ID: <20040331171023.GA4543@in.ibm.com> References: <20040329222926.GF3808@dualathlon.random> <200403302005.AAA00466@yakov.inr.ac.ru> <20040330211450.GI3808@dualathlon.random> <20040330133000.098761e2.davem@redhat.com> <20040330213742.GL3808@dualathlon.random> Reply-To: dipankar@in.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "David S. Miller" , kuznet@ms2.inr.ac.ru, linux-kernel@vger.kernel.org, netdev@oss.sgi.com, Robert.Olsson@data.slu.se, paulmck@us.ibm.com, akpm@osdl.org Return-path: To: Andrea Arcangeli Content-Disposition: inline In-Reply-To: <20040330213742.GL3808@dualathlon.random> Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Tue, Mar 30, 2004 at 11:37:42PM +0200, Andrea Arcangeli wrote: > On Tue, Mar 30, 2004 at 01:30:00PM -0800, David S. Miller wrote: > > On Tue, 30 Mar 2004 23:14:50 +0200 > > Andrea Arcangeli wrote: > > > > > > There are no hardirqs in the case under investigation, remember? > > > > > > no hardirqs? there must be tons of hardirqs if ksoftirqd never runs. > > > > NAPI should be kicking in for this workload, and I know for a fact it is > > for Robert's case. There should only be a few thousand hard irqs per > > second. > > > > Until the RX ring is depleted the device's hardirqs will not be re- > > enabled. > > then Dipankar is reproducing with a workload that is completely > different. I've only seen the emails from Dipankar so I couldn't know it > was a NAPI load. > > He posted these numbers: > > softirq_count, ksoftirqd_count and other_softirq_count shows - > > CPU 0 : 638240 554 637686 > CPU 1 : 102316 1 102315 > CPU 2 : 675696 557 675139 > CPU 3 : 102305 0 102305 > > that means nothing runs in ksoftirqd for Dipankar, so he cannot be using > NAPI. And I am not. I am still on 2.6.0 and there seems to be no NAPI support for the e100 there. Should I try 2.6.4 where e100 has NAPI support ? Anyway, even without softirqs on the back of hardirqs, there are other ways of softirq overload as seen in Robert's setup. Thanks Dipankar