Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755118AbaDAX5e (ORCPT ); Tue, 1 Apr 2014 19:57:34 -0400 Received: from e32.co.us.ibm.com ([32.97.110.150]:58039 "EHLO e32.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752567AbaDAX53 (ORCPT ); Tue, 1 Apr 2014 19:57:29 -0400 Date: Tue, 1 Apr 2014 16:57:24 -0700 From: "Paul E. McKenney" To: Dave Jones , Linux Kernel Subject: Re: rcu_prempt stalls / lockup Message-ID: <20140401235724.GD4284@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20140401004801.GQ4284@linux.vnet.ibm.com> <20140401150849.GA14757@redhat.com> <20140401153032.GT4284@linux.vnet.ibm.com> <20140401172244.GA10363@redhat.com> <20140401175545.GV4284@linux.vnet.ibm.com> <20140401180414.GA12326@redhat.com> <20140401183245.GA12473@linux.vnet.ibm.com> <20140401221616.GA961@redhat.com> <20140401231822.GC4284@linux.vnet.ibm.com> <20140401233130.GA25030@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140401233130.GA25030@redhat.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14040123-0928-0000-0000-000000ECFC36 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Apr 01, 2014 at 07:31:30PM -0400, Dave Jones wrote: > On Tue, Apr 01, 2014 at 04:18:22PM -0700, Paul E. McKenney wrote: > > > > # entries-in-buffer/entries-written: 7/7 #P:4 > > > # > > > # _-----=> irqs-off > > > # / _----=> need-resched > > > # | / _---=> hardirq/softirq > > > # || / _--=> preempt-depth > > > # ||| / delay > > > # TASK-PID CPU# |||| TIMESTAMP FUNCTION > > > # | | | |||| | | > > > -0 [000] dNs3 851.748475: rcu_grace_period: rcu_preempt 21342 cpuend > > > -0 [000] dNs3 851.748477: rcu_grace_period: rcu_preempt 21343 cpustart > > > -0 [000] dNs3 851.748477: rcu_grace_period: rcu_sched 20080 cpuend > > > -0 [000] dN.2 851.748480: rcu_grace_period: rcu_preempt 21343 cpuqs > > > rcu_preempt-9 [000] ...1 851.748485: rcu_grace_period: rcu_preempt 21343 fqsstart > > > rcu_preempt-9 [000] ...1 851.748487: rcu_grace_period: rcu_preempt 21343 fqsend > > > rcu_preempt-9 [000] ...1 851.748487: rcu_grace_period: rcu_preempt 21343 fqswait > > > # tracer: nop > > > # > > > # entries-in-buffer/entries-written: 13/13 #P:4 > > > # > > > # _-----=> irqs-off > > > # / _----=> need-resched > > > # | / _---=> hardirq/softirq > > > # || / _--=> preempt-depth > > > # ||| / delay > > > # TASK-PID CPU# |||| TIMESTAMP FUNCTION > > > # | | | |||| | | > > > rcu_preempt-9 [003] d..2 851.878457: rcu_grace_period: rcu_preempt 21349 end > > > rcu_preempt-9 [003] d..2 851.878459: rcu_grace_period: rcu_preempt 21349 newreq > > > rcu_preempt-9 [003] ...1 851.878459: rcu_grace_period: rcu_preempt 21349 reqwait > > > rcu_preempt-9 [003] d..2 851.878460: rcu_grace_period: rcu_preempt 21350 start > > > rcu_preempt-9 [003] d..2 851.878461: rcu_grace_period: rcu_preempt 21350 cpustart > > > rcu_preempt-9 [003] d..2 851.878462: rcu_grace_period_init: rcu_preempt 21350 0 0 7 f > > > rcu_preempt-9 [003] ...1 851.878463: rcu_grace_period: rcu_preempt 21350 fqswait > > > rcu_preempt-9 [003] d..2 851.878464: rcu_grace_period: rcu_preempt 21350 cpuqs > > > -0 [000] dNs3 851.878482: rcu_grace_period: rcu_preempt 21349 cpuend > > > -0 [000] dNs3 851.878483: rcu_grace_period: rcu_preempt 21350 cpustart > > > -0 [000] dNs3 851.878484: rcu_grace_period: rcu_sched 20086 cpuend > > > -0 [000] .N.2 851.878486: rcu_grace_period: rcu_sched 20086 cpuqs > > > -0 [000] dN.2 851.878487: rcu_grace_period: rcu_preempt 21350 cpuqs OK, so the trace ended on grace period #21350... > > > > > > > > > followed by a half dozen 'empty' traces before it totally locked up. > > > > Cool, thank you! > > > > Could you please also send the RCU CPU stall warning messages? > > >From that run they were.. > > [ 917.790265] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 917.791189] (detected by 0, t=6502 jiffies, g=21390, c=21389, q=0) But the hang didn't happen until grace period #21390. Sigh! That means that the trace doesn't tell me about the current grace period. Thank you for getting this info, but it is beginning to look like bisection is necessary here. :-( Thanx, Paul > [ 917.792058] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 917.792799] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 917.793534] (detected by 0, t=6502 jiffies, g=20128, c=20127, q=0) > [ 917.794265] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1112.727480] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 1112.728425] (detected by 0, t=26007 jiffies, g=21390, c=21389, q=0) > [ 1112.729300] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1112.730035] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 1112.730744] (detected by 0, t=26007 jiffies, g=20128, c=20127, q=0) > [ 1112.731459] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1307.664710] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 1307.665623] (detected by 0, t=45512 jiffies, g=21390, c=21389, q=0) > [ 1307.666386] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1307.667113] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 1307.667839] (detected by 0, t=45512 jiffies, g=20128, c=20127, q=0) > [ 1307.668572] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1502.601961] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 1502.602905] (detected by 0, t=65017 jiffies, g=21390, c=21389, q=0) > [ 1502.603765] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1502.604550] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 1502.605305] (detected by 0, t=65017 jiffies, g=20128, c=20127, q=0) > [ 1502.606061] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1697.539217] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 1697.540189] (detected by 0, t=84522 jiffies, g=21390, c=21389, q=0) > [ 1697.541052] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1697.541826] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 1697.542600] (detected by 0, t=84522 jiffies, g=20128, c=20127, q=0) > [ 1697.543378] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1892.476433] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 1892.477545] (detected by 0, t=104027 jiffies, g=21390, c=21389, q=0) > [ 1892.478402] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 1892.479208] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 1892.480010] (detected by 0, t=104027 jiffies, g=20128, c=20127, q=0) > [ 1892.480831] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 2087.413694] INFO: rcu_preempt detected stalls on CPUs/tasks: > [ 2087.414748] (detected by 0, t=123532 jiffies, g=21390, c=21389, q=0) > [ 2087.415722] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > [ 2087.416558] INFO: rcu_sched detected stalls on CPUs/tasks: > [ 2087.417392] (detected by 0, t=123532 jiffies, g=20128, c=20127, q=0) > [ 2087.418231] INFO: Stall ended before state dump start, gp_kthread state: 0x2 > > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/