From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751471AbcGNXww (ORCPT ); Thu, 14 Jul 2016 19:52:52 -0400 Received: from mail-pa0-f52.google.com ([209.85.220.52]:34390 "EHLO mail-pa0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751224AbcGNXwt (ORCPT ); Thu, 14 Jul 2016 19:52:49 -0400 Date: Thu, 14 Jul 2016 16:52:46 -0700 From: Viresh Kumar To: Sergey Senozhatsky Cc: Petr Mladek , Sergey Senozhatsky , Jan Kara , Tejun Heo , Greg Kroah-Hartman , Linux Kernel Mailing List , vlevenetz@mm-sol.com, vaibhav.hiremath@linaro.org, alex.elder@linaro.org, johan@kernel.org, akpm@linux-foundation.org, rostedt@goodmis.org Subject: Re: [Query] Preemption (hogging) of the work handler Message-ID: <20160714235246.GI3057@ubuntu> References: <20160701165959.GR12473@ubuntu> <20160701172232.GD28719@htj.duckdns.org> <20160706182842.GS2671@ubuntu> <20160711102603.GI12410@quack2.suse.cz> <20160711154438.GA528@swordfish> <20160711223501.GI4695@ubuntu> <20160712093805.GA498@swordfish> <20160712125243.GA8597@pathway.suse.cz> <20160712140300.GA520@swordfish> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160712140300.GA520@swordfish> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Sorry, but I failed to do any testing on this and answer the questions you raise. But I saw this again today and here are some important points. On 12-07-16, 23:03, Sergey Senozhatsky wrote: > so, I'm looking at this thing now: > > : [ 12.874909] sched: RT throttling activated for rt_rq ffffffc0ac13fcd0 (cpu 0) > : [ 12.874909] potential CPU hogs: > : [ 12.874909] printk (292) > > so it's either cond_resched() does not reshed, keeping printk kthread > active, which, however, upsets the sched and triggers throttling (umm, what); > > or we, somehow, have `console_may_schedule == 0' in this final console_unlock(), > so cond_resched() never happens. > > I'm looking at mainline 3.10, tho. > > Viresh, can you verify if we can do cond_resched() from console_unlock() > (console_may_schedule != 0) ? I have hit this throttling issue twice and both were under the same circumstances. Explaining in case it can help us debug it further :) - Happens during early boot of the phone, ~10 seconds. - Userspace noted that there are some issues with Android filesystem, like /system/bin/sh not found and so it says: init: cannot find '/system/bin/sh' (No such file or directory), disabling 'console' - Userspace noticed that something is wrong and its good to reboot phone in another mode. - But before that it dumps the kernel-messages from last boot and the prints looked like this: [ 12.805180] [ 7.919623] **Some Kernel Messages here** Double time-stamp here, because one was already present in the last KMSG (logs from previous boot). After around 100 lines got printed, we had this throttling messages (without the double timestamp), and we continue to print things after it as well. -- viresh