From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Re: 2.6.39-rc4+: Kernel leaking memory during FS scanning, regression? Date: Wed, 27 Apr 2011 15:27:27 -0700 Message-ID: <20110427222727.GU2135@linux.vnet.ibm.com> References: <20110425214933.GO2468@linux.vnet.ibm.com> <20110426081904.0d2b1494@pluto.restena.lu> <20110426112756.GF4308@linux.vnet.ibm.com> <20110426183859.6ff6279b@neptune.home> <20110426190918.01660ccf@neptune.home> <20110427081501.5ba28155@pluto.restena.lu> <20110427204139.1b0ea23b@neptune.home> Reply-To: paulmck@linux.vnet.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Bruno =?iso-8859-1?Q?Pr=E9mont?= , Linus Torvalds , Ingo Molnar , Peter Zijlstra , Mike Frysinger , KOSAKI Motohiro , linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, "Paul E. McKenney" , Pekka Enberg To: Thomas Gleixner Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On Thu, Apr 28, 2011 at 12:06:11AM +0200, Thomas Gleixner wrote: > On Wed, 27 Apr 2011, Bruno Pr=E9mont wrote: > > On Wed, 27 April 2011 Bruno Pr=E9mont wrote: > > Voluntary context switches stay constant from the time on SLABs pil= e up. > > (which makes sense as it doesn't run get CPU slices anymore) > >=20 > > > > Can you please enable CONFIG_SCHED_DEBUG and provide the output= of > > > > /proc/sched_stat when the problem surfaces and a minute after t= he > > > > first snapshot? > >=20 > > hm, did you mean CONFIG_SCHEDSTAT or /proc/sched_debug? > >=20 > > I did use CONFIG_SCHED_DEBUG (and there is no /proc/sched_stat) so = I took > > /proc/sched_debug which exists... (attached, taken about 7min and += 1min > > after SLABs started piling up), though build processes were SIGSTOP= ped > > during first minute. >=20 > Oops. /proc/sched_debug is the right thing. >=20 > > printk wrote (in case its timestamp is useful, more below): > > [ 518.480103] sched: RT throttling activated >=20 > Ok. Aside of the fact that the CPU time accounting is completely hose= d > this is pointing to the root cause of the problem. >=20 > kthread_rcu seems to run in circles for whatever reason and the RT > throttler catches it. After that things go down the drain completely > as it should get on the CPU again after that 50ms throttling break. Ah. This could happen if there was a huge number of callbacks, in which case blimit would be set very large and kthread_rcu could then go CPU-bound. And this workload was generating large numbers of callbacks due to filesystem operations, right? So, perhaps I should kick kthread_rcu back to SCHED_NORMAL if blimit has been set high. Or have some throttling of my own. I must confess that throttling kthread_rcu for two hours seems a bit harsh. ;-) If this was just throttling kthread_rcu for a few hundred milliseconds, or even for a second or two, things would be just fine. Left to myself, I will put together a patch that puts callback processi= ng down to SCHED_NORMAL in the case where there are huge numbers of callbacks to be processed. > Though we should not ignore the fact, that the RT throttler hit, but > none of the RT tasks actually accumulated runtime. >=20 > So there is a couple of questions: >=20 > - Why does the scheduler detect the 950 ms RT runtime, but does > not accumulate that runtime to any thread >=20 > - Why is the runtime accounting totally hosed >=20 > - Why does that not happen (at least not reproducible) with=20 > TREE_RCU This one I can answer -- In Linus's tree, TREE_RCU still uses softirq, so there is no RCU kthread, so there is nothing to throttle other than ksoftirqd itself. Thanx, Paul > I need some sleep now, but I will try to come up with sensible > debugging tomorrow unless Paul or someone else beats me to it. >=20 > Thanks, >=20 > tglx