From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesper Dangaard Brouer Subject: Re: [PATCH] softirq: let ksoftirqd do its job Date: Fri, 2 Sep 2016 10:35:34 +0200 Message-ID: <20160902103534.670b8f6a@redhat.com> References: <1472665349.14381.356.camel@edumazet-glaptop3.roam.corp.google.com> <20160831214043.2f44cf08@redhat.com> <1472676150.14381.363.camel@edumazet-glaptop3.roam.corp.google.com> <20160831235116.33b1946b@redhat.com> <20160901130231.58355405@redhat.com> <20160901115356.GT10153@twins.programming.kicks-ass.net> <20160901142925.63a5031b@redhat.com> <20160901143859.730826ed@redhat.com> <20160901124839.GU10153@twins.programming.kicks-ass.net> <20160901153042.465b864e@redhat.com> <20160901152802.GV10153@twins.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Eric Dumazet , David Miller , Rik van Riel , Paolo Abeni , Hannes Frederic Sowa , linux-kernel , netdev , Jonathan Corbet , brouer@redhat.com To: Peter Zijlstra Return-path: In-Reply-To: <20160901152802.GV10153@twins.programming.kicks-ass.net> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Thu, 1 Sep 2016 17:28:02 +0200 Peter Zijlstra wrote: > On Thu, Sep 01, 2016 at 03:30:42PM +0200, Jesper Dangaard Brouer wrote: > > Still... enabled! > > Hmmm.. more idea how to disable this??? > > I think you ought to be able to assign yourself to the root cgroup, > something like: > > echo $$ > /cgroup/tasks > > or wheverever the cpu-cgroup controller is mounted at. > > But its been a fair while since I touched any of that, its not a CONFIG > I have enabled much. I could not figure out how to disable autogroups, so I ended up compiling the kernel without CONFIG_SCHED_AUTOGROUP. PID PR S %CPU TIME+ COMMAND 3 20 R 20.7 0:53.05 ksoftirqd/0 9299 20 R 16.3 0:03.62 udp_sink 9296 20 S 16.0 0:03.59 udp_sink 9297 20 R 16.0 0:03.58 udp_sink 9298 20 R 16.0 0:03.57 udp_sink 9295 20 R 15.3 0:03.43 udp_sink Top new shows the CPU distribution is more correct, thus we can concluded the artifact I saw was indeed caused by autogroup. I can also confirm that my netperf UDP_STREAM tests now work again, but I need around 32 parallel netperf to counter the effectiveness of the ksoftirqd process. While I only need 5 udp_sink programs. -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat Author of http://www.iptv-analyzer.org LinkedIn: http://www.linkedin.com/in/brouer