From mboxrd@z Thu Jan 1 00:00:00 1970 From: Steven Rostedt Subject: Re: [PATCH][RT] netpoll: Always take poll_lock when doing polling Date: Fri, 10 Jun 2016 12:45:25 -0400 Message-ID: <20160610124525.32cac2e0@gandalf.local.home> References: <20160526195641.6c26e979@gandalf.local.home> <20160602161235.GA12971@linutronix.de> <20160604071131.08d449db@grimm.local.home> <20160610155717.GB10775@linutronix.de> <20160610121118.03f281e8@gandalf.local.home> <8582eb37-3b5b-ee7e-3a67-8f4609b0ac3f@linutronix.de> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: alison@peloton-tech.com, LKML , linux-rt-users , netdev , Thomas Gleixner , Peter Zijlstra , Clark Williams , Eric Dumazet , David Miller To: Sebastian Andrzej Siewior Return-path: In-Reply-To: <8582eb37-3b5b-ee7e-3a67-8f4609b0ac3f@linutronix.de> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On Fri, 10 Jun 2016 18:20:22 +0200 Sebastian Andrzej Siewior wrote: > > We actually triggered a starvation due to this. I was just seeing if > > Alison hit the same issue we did in our tests. > > Okay. Didn't get this information from him. But this is only because > the softirqs not running in ksoftirqd, right? Right, I think we supplied this patch before we added the one that would push repeated softirqs to ksoftirqd. We probably should see if that patch alone fixes our issue. -- Steve