From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Sachin Sant <sachinp@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Matt Fleming <matt@codeblueprint.co.uk>,
"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
Mike Galbraith <efault@gmx.de>,
LKML <linux-kernel@vger.kernel.org>,
"linux-next@vger.kernel.org" <linux-next@vger.kernel.org>,
Ross Zwisler <zwisler@gmail.com>
Subject: Re: [tip:sched/core] sched/core: Add debugging code to catch missing update_rq_clock() calls
Date: Mon, 6 Feb 2017 07:10:48 -0800 [thread overview]
Message-ID: <20170206151048.GK30506@linux.vnet.ibm.com> (raw)
In-Reply-To: <45DC157B-EA1A-4E1C-9449-8DD317837FCB@linux.vnet.ibm.com>
On Mon, Feb 06, 2017 at 11:53:10AM +0530, Sachin Sant wrote:
>
> >>> I've seen it on tip. It looks like hot unplug goes really slow when
> >>> there's running tasks on the CPU being taken down.
> >>>
> >>> What I did was something like:
> >>>
> >>> taskset -p $((1<<1)) $$
> >>> for ((i=0; i<20; i++)) do while :; do :; done & done
> >>>
> >>> taskset -p $((1<<0)) $$
> >>> echo 0 > /sys/devices/system/cpu/cpu1/online
> >>>
> >>> And with those 20 tasks stuck sucking cycles on CPU1, the unplug goes
> >>> _really_ slow and the RCU stall triggers. What I suspect happens is that
> >>> hotplug stops participating in the RCU state machine early, but only
> >>> tells RCU about it really late, and in between it gets suspicious it
> >>> takes too long.
> >>>
> >>> I've yet to dig through the RCU code to figure out the exact sequence of
> >>> events, but found the above to be fairly reliable in triggering the
> >>> issue.
> >
> >> If you send me the full splat from the dmesg and the RCU portions of
> >> .config, I will take a look. Is this new behavior, or a new test?
> >
>
> I have sent the required files to you via separate email.
>
> > If new behavior, I would be most suspicious of these commits in -rcu which
> > recently entered -tip:
> >
> > 19e4d983cda1 rcu: Place guard on rcu_all_qs() and rcu_note_context_switch() actions
> > 913324b1364f rcu: Eliminate flavor scan in rcu_momentary_dyntick_idle()
> > fcdcfefafa45 rcu: Pull rcu_qs_ctr into rcu_dynticks structure
> > 0919a0b7e7a5 rcu: Pull rcu_sched_qs_mask into rcu_dynticks structure
> > caa7c8e34293 rcu: Make rcu_note_context_switch() do deferred NOCB wakeups
> > 41e4b159d516 rcu: Make rcu_all_qs() do deferred NOCB wakeups
> > b457a3356a68 rcu: Make call_rcu() do deferred NOCB wakeups
> >
> > Does reverting any of these help?
>
> I tried reverting the above commits. That does not help. I can still recreate the issue.
Thank you for testing, Sachin!
Could you please try building and testing with CONFIG_RCU_BOOST=y?
You will need to enable CONFIG_RCU_EXPERT=y to see this Kconfig option.
Thanx, Paul
next prev parent reply other threads:[~2017-02-06 15:10 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-21 13:38 [PATCH v2 0/7] sched: Diagnostic checks for missing rq clock updates Matt Fleming
2016-09-21 13:38 ` [PATCH v2 1/7] sched/fair: Update the rq clock before detaching tasks Matt Fleming
2016-10-03 12:49 ` Peter Zijlstra
2016-10-03 14:37 ` Matt Fleming
2016-10-03 14:42 ` Peter Zijlstra
2016-09-21 13:38 ` [PATCH v2 2/7] sched/fair: Update rq clock before waking up new task Matt Fleming
2016-09-21 13:38 ` [PATCH v2 3/7] sched/fair: Update rq clock in task_hot() Matt Fleming
2016-09-21 13:38 ` [PATCH v2 4/7] sched: Add wrappers for lockdep_(un)pin_lock() Matt Fleming
2017-01-14 12:40 ` [tip:sched/core] sched/core: " tip-bot for Matt Fleming
2016-09-21 13:38 ` [PATCH v2 5/7] sched/core: Reset RQCF_ACT_SKIP before unpinning rq->lock Matt Fleming
2017-01-14 12:41 ` [tip:sched/core] " tip-bot for Matt Fleming
2016-09-21 13:38 ` [PATCH v2 6/7] sched/fair: Push rq lock pin/unpin into idle_balance() Matt Fleming
2017-01-14 12:41 ` [tip:sched/core] " tip-bot for Matt Fleming
2016-09-21 13:38 ` [PATCH v2 7/7] sched/core: Add debug code to catch missing update_rq_clock() Matt Fleming
2016-09-21 15:58 ` Petr Mladek
2016-09-21 19:08 ` Matt Fleming
2016-09-21 19:46 ` Thomas Gleixner
2016-09-22 0:44 ` Sergey Senozhatsky
2016-09-22 8:04 ` Peter Zijlstra
2016-09-22 8:36 ` Jan Kara
2016-09-22 9:39 ` Peter Zijlstra
2016-09-22 10:17 ` Peter Zijlstra
2017-01-14 12:44 ` [tip:sched/core] sched/core: Add debugging code to catch missing update_rq_clock() calls tip-bot for Matt Fleming
[not found] ` <87tw8gutp6.fsf@concordia.ellerman.id.au>
2017-01-30 21:34 ` Matt Fleming
2017-01-31 8:35 ` Michael Ellerman
2017-01-31 11:00 ` Sachin Sant
2017-01-31 11:48 ` Mike Galbraith
2017-01-31 17:22 ` Ross Zwisler
2017-02-02 15:55 ` Peter Zijlstra
2017-02-02 22:01 ` Matt Fleming
2017-02-03 3:05 ` Mike Galbraith
2017-02-03 4:33 ` Sachin Sant
2017-02-03 8:53 ` Peter Zijlstra
2017-02-03 12:59 ` Mike Galbraith
2017-02-03 13:37 ` Peter Zijlstra
2017-02-03 13:52 ` Mike Galbraith
2017-02-03 15:44 ` Paul E. McKenney
2017-02-03 15:54 ` Paul E. McKenney
2017-02-06 6:23 ` Sachin Sant
2017-02-06 15:10 ` Paul E. McKenney [this message]
2017-02-06 15:14 ` Paul E. McKenney
2017-02-03 13:04 ` Borislav Petkov
2017-02-22 9:03 ` Wanpeng Li
2017-02-24 9:16 ` [tip:sched/urgent] sched/core: Fix update_rq_clock() splat on hotplug (and suspend/resume) tip-bot for Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170206151048.GK30506@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-next@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=matt@codeblueprint.co.uk \
--cc=peterz@infradead.org \
--cc=sachinp@linux.vnet.ibm.com \
--cc=zwisler@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).