From: SeongJae Park <sjpark@amazon.com>
To: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
SeongJae Park <sjpark@amazon.com>,
Eric Dumazet <edumazet@google.com>,
David Miller <davem@davemloft.net>,
"Al Viro" <viro@zeniv.linux.org.uk>,
Jakub Kicinski <kuba@kernel.org>,
"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
<sj38.park@gmail.com>, netdev <netdev@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
SeongJae Park <sjpark@amazon.de>, <snu@amazon.com>,
<amit@kernel.org>, <stable@vger.kernel.org>
Subject: Re: Re: [PATCH net v2 0/2] Revert the 'socket_alloc' life cycle change
Date: Tue, 5 May 2020 19:49:43 +0200 [thread overview]
Message-ID: <20200505174943.10384-1-sjpark@amazon.com> (raw)
In-Reply-To: <20200505172358.GC2869@paulmck-ThinkPad-P72> (raw)
On Tue, 5 May 2020 10:23:58 -0700 "Paul E. McKenney" <paulmck@kernel.org> wrote:
> On Tue, May 05, 2020 at 09:25:06AM -0700, Eric Dumazet wrote:
> >
> >
> > On 5/5/20 9:13 AM, SeongJae Park wrote:
> > > On Tue, 5 May 2020 09:00:44 -0700 Eric Dumazet <edumazet@google.com> wrote:
> > >
> > >> On Tue, May 5, 2020 at 8:47 AM SeongJae Park <sjpark@amazon.com> wrote:
> > >>>
> > >>> On Tue, 5 May 2020 08:20:50 -0700 Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > >>>
> > >>>>
> > >>>>
> > >>>> On 5/5/20 8:07 AM, SeongJae Park wrote:
> > >>>>> On Tue, 5 May 2020 07:53:39 -0700 Eric Dumazet <edumazet@google.com> wrote:
> > >>>>>
> > >>>>
> > >>>>>> Why do we have 10,000,000 objects around ? Could this be because of
> > >>>>>> some RCU problem ?
> > >>>>>
> > >>>>> Mainly because of a long RCU grace period, as you guess. I have no idea how
> > >>>>> the grace period became so long in this case.
> > >>>>>
> > >>>>> As my test machine was a virtual machine instance, I guess RCU readers
> > >>>>> preemption[1] like problem might affected this.
> > >>>>>
> > >>>>> [1] https://www.usenix.org/system/files/conference/atc17/atc17-prasad.pdf
>
> If this is the root cause of the problem, then it will be necessary to
> provide a hint to the hypervisor. Or, in the near term, avoid loading
> the hypervisor the point that vCPU preemption is so lengthy.
>
> RCU could also provide some sort of pre-stall-warning notification that
> some of the CPUs aren't passing through quiescent states, which might
> allow the guest OS's userspace to take corrective action.
>
> But first, what are you doing to either confirm or invalidate the
> hypothesis that this might be due to vCPU preemption?
Nothing, I was just guessing. Sorry if this made you confused.
>
> > >>>>>> Once Al patches reverted, do you have 10,000,000 sock_alloc around ?
> > >>>>>
> > >>>>> Yes, both the old kernel that prior to Al's patches and the recent kernel
> > >>>>> reverting the Al's patches didn't reproduce the problem.
> > >>>>>
> > >>>>
> > >>>> I repeat my question : Do you have 10,000,000 (smaller) objects kept in slab caches ?
> > >>>>
> > >>>> TCP sockets use the (very complex, error prone) SLAB_TYPESAFE_BY_RCU, but not the struct socket_wq
> > >>>> object that was allocated in sock_alloc_inode() before Al patches.
> > >>>>
> > >>>> These objects should be visible in kmalloc-64 kmem cache.
> > >>>
> > >>> Not exactly the 10,000,000, as it is only the possible highest number, but I
> > >>> was able to observe clear exponential increase of the number of the objects
> > >>> using slabtop. Before the start of the problematic workload, the number of
> > >>> objects of 'kmalloc-64' was 5760, but I was able to observe the number increase
> > >>> to 1,136,576.
> > >>>
> > >>> OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
> > >>> before: 5760 5088 88% 0.06K 90 64 360K kmalloc-64
> > >>> after: 1136576 1136576 100% 0.06K 17759 64 71036K kmalloc-64
> > >>>
> > >>
> > >> Great, thanks.
> > >>
> > >> How recent is the kernel you are running for your experiment ?
> > >
> > > It's based on 5.4.35.
>
> Is it possible to retest on v5.6? I have been adding various mechanisms
> to make RCU keep up better with heavy callback overload.
I will try soon!
>
> Also, could you please provide the .config? If either NO_HZ_FULL or
> RCU_NOCB_CPU, please also provide the kernel boot parameters.
NO_HZ_FULL is not set, but RCU_NOCB_CPU is y.
I think I should check whether it's ok to share the full config and boot
parameters. Please wait this.
>
> > >> Let's make sure the bug is not in RCU.
> > >
> > > One thing I can currently say is that the grace period passes at last. I
> > > modified the benchmark to repeat not 10,000 times but only 5,000 times to run
> > > the test without OOM but easily observable memory pressure. As soon as the
> > > benchmark finishes, the memory were freed.
> > >
> > > If you need more tests, please let me know.
> >
> > I would ask Paul opinion on this issue, because we have many objects
> > being freed after RCU grace periods.
>
> As always, "It depends."
>
> o If the problem is a too-long RCU reader, RCU is prohibited from
> ending the grace period. The reader duration must be shortened,
> and until it is shortened, there is nothing RCU can do.
>
> o In some special cases of the above, RCU can and does help, for
> example, by enlisting the aid of cond_resched(). So perhaps
> there is a long in-kernel loop that needs a cond_resched().
>
> And perhaps RCU can help for some types of vCPU preemption.
>
> o As Al suggested offline and as has been discussed in the past,
> it would not be hard to cause RCU to burn CPU to attain faster
> grace periods during OOM events. This could be helpful, but only
> given that RCU readers are completing in reasonable timeframes.
Totally agreed.
>
> > If RCU subsystem can not keep-up, I guess other workloads will also suffer.
>
> If readers are not excessively long, RCU should be able to keep up.
> (In the absence of misconfigurations, for example, both NO_HZ_FULL and
> then binding all the rcuo kthreads to a single CPU on a 100-CPU system
> or some such.)
>
> > Sure, we can revert patches there and there trying to work around the issue,
> > but for objects allocated from process context, we should not have these problems.
>
> Agreed, let's get more info on what is happening to RCU.
>
> One approach is to shorten the RCU CPU stall warning timeout
> (rcupdate.rcu_cpu_stall_timeout=10 for 10 seconds).
I will also try this and let you know the results.
Thanks,
SeongJae Park
>
> Thanx, Paul
next prev parent reply other threads:[~2020-05-05 17:50 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-05 8:10 [PATCH net v2 0/2] Revert the 'socket_alloc' life cycle change SeongJae Park
2020-05-05 8:10 ` [PATCH net v2 1/2] Revert "coallocate socket_wq with socket itself" SeongJae Park
2020-05-06 4:55 ` kbuild test robot
2020-05-05 8:10 ` [PATCH net v2 2/2] Revert "sockfs: switch to ->free_inode()" SeongJae Park
2020-05-05 11:54 ` [PATCH net v2 0/2] Revert the 'socket_alloc' life cycle change SeongJae Park
2020-05-05 12:31 ` Nuernberger, Stefan
2020-05-05 14:53 ` Eric Dumazet
2020-05-05 15:07 ` SeongJae Park
2020-05-05 15:20 ` Eric Dumazet
2020-05-05 15:46 ` SeongJae Park
2020-05-05 16:00 ` Eric Dumazet
2020-05-05 16:13 ` SeongJae Park
2020-05-05 16:25 ` Eric Dumazet
2020-05-05 16:31 ` Eric Dumazet
2020-05-05 16:37 ` Eric Dumazet
2020-05-05 17:05 ` SeongJae Park
2020-05-05 17:30 ` Paul E. McKenney
2020-05-05 17:56 ` SeongJae Park
2020-05-05 18:17 ` Paul E. McKenney
2020-05-05 18:34 ` SeongJae Park
2020-05-05 18:49 ` Paul E. McKenney
2020-05-06 12:59 ` SeongJae Park
2020-05-06 14:33 ` Eric Dumazet
2020-05-06 14:41 ` Paul E. McKenney
2020-05-06 15:20 ` SeongJae Park
2020-05-05 17:28 ` Paul E. McKenney
2020-05-05 18:11 ` SeongJae Park
2020-05-05 17:23 ` Paul E. McKenney
2020-05-05 17:49 ` SeongJae Park [this message]
2020-05-05 18:27 ` Paul E. McKenney
2020-05-05 18:40 ` SeongJae Park
2020-05-05 18:48 ` Paul E. McKenney
2020-05-05 16:26 ` Al Viro
2020-05-05 18:48 ` David Miller
2020-05-05 19:00 ` David Miller
2020-05-06 6:24 ` SeongJae Park
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=20200505174943.10384-1-sjpark@amazon.com \
--to=sjpark@amazon.com \
--cc=amit@kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=gregkh@linuxfoundation.org \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=sj38.park@gmail.com \
--cc=sjpark@amazon.de \
--cc=snu@amazon.com \
--cc=stable@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
/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).