From: Yosry Ahmed <yosryahmed@google.com>
To: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>, Josef Bacik <josef@toxicpanda.com>,
Jens Axboe <axboe@kernel.dk>, Zefan Li <lizefan.x@bytedance.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Roman Gushchin <roman.gushchin@linux.dev>,
Muchun Song <muchun.song@linux.dev>,
Andrew Morton <akpm@linux-foundation.org>,
Vasily Averin <vasily.averin@linux.dev>,
cgroups@vger.kernel.org, linux-block@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
bpf@vger.kernel.org
Subject: Re: [RFC PATCH 1/7] cgroup: rstat: only disable interrupts for the percpu lock
Date: Thu, 23 Mar 2023 06:35:44 -0700 [thread overview]
Message-ID: <CAJD7tkY6Wf2OWja+f-JeFM5DdMCyLzbXxZ8KF0MjcYOKri-vtA@mail.gmail.com> (raw)
In-Reply-To: <CALvZod5GT=bZsLXsG500pNkEJpMB1o2KJau4=r0eHB-c8US53A@mail.gmail.com>
On Wed, Mar 22, 2023 at 11:33 PM Shakeel Butt <shakeelb@google.com> wrote:
>
> On Wed, Mar 22, 2023 at 10:15 PM Yosry Ahmed <yosryahmed@google.com> wrote:
> >
> [...]
> > > Couple of questions:
> > >
> > > 1. What exactly is cgroup_rstat_lock protecting? Can we just remove it
> > > altogether?
> >
> > I believe it protects the global state variables that we flush into.
> > For example, for memcg, it protects mem_cgroup->vmstats.
> >
> > I tried removing the lock and allowing concurrent flushing on
> > different cpus, by changing mem_cgroup->vmstats to use atomics
> > instead, but that turned out to be a little expensive. Also,
> > cgroup_rstat_lock is already contended by different flushers
> > (mitigated by stats_flush_lock on the memcg side). If we remove it,
> > concurrent flushers contend on every single percpu lock instead, which
> > also seems to be expensive.
>
> We should add a comment on what it is protecting. I think block rstat
> are fine but memcg and bpf would need this.
I think it also protects the cpu base stats flushed by cgroup_base_stat_flush().
I will add a comment in the next version.
>
> >
> > > 2. Are we really calling rstat flush in irq context?
> >
> > I think it is possible through the charge/uncharge path:
> > memcg_check_events()->mem_cgroup_threshold()->mem_cgroup_usage(). I
> > added the protection against flushing in an interrupt context for
> > future callers as well, as it may cause a deadlock if we don't disable
> > interrupts when acquiring cgroup_rstat_lock.
> >
> > > 3. The mem_cgroup_flush_stats() call in mem_cgroup_usage() is only
> > > done for root memcg. Why is mem_cgroup_threshold() interested in root
> > > memcg usage? Why not ignore root memcg in mem_cgroup_threshold() ?
> >
> > I am not sure, but the code looks like event notifications may be set
> > up on root memcg, which is why we need to check thresholds.
>
> This is something we should deprecate as root memcg's usage is ill defined.
Right, but I think this would be orthogonal to this patch series.
>
> >
> > Even if mem_cgroup_threshold() does not flush memcg stats, the purpose
> > of this patch is to make sure the rstat flushing code itself is not
> > disabling interrupts; which it currently does for any unsleepable
> > context, even if it is interruptible.
>
> Basically I am saying we should aim for VM_BUG_ON(!in_task()) in the
> flush function rather than adding should_skip_flush() which does not
> stop potential new irq flushers.
I wanted to start with VM_BUG_ON(!in_task()) but I wasn't sure that
all contexts that call rstat flushing are not in irq contexts. I added
should_skip_flush() so that if there are existing flushers in irq
context, or new flushers are added, we are protected against a
deadlock.
We can change should_skip_flush() to have a WARN_ON_ONCE(!in_task())
to alert in this case. If you prefer removing should_skip_flush() and
just adding VM_BUG_ON(!in_task()) we can do that, but personally I was
not confident enough that we have no code paths today that may attempt
flushing from irq context.
next prev parent reply other threads:[~2023-03-23 13:36 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-23 4:00 [RFC PATCH 0/7] Make rstat flushing IRQ and sleep friendly Yosry Ahmed
2023-03-23 4:00 ` [RFC PATCH 1/7] cgroup: rstat: only disable interrupts for the percpu lock Yosry Ahmed
2023-03-23 4:29 ` Shakeel Butt
2023-03-23 5:15 ` Yosry Ahmed
2023-03-23 6:33 ` Shakeel Butt
2023-03-23 13:35 ` Yosry Ahmed [this message]
2023-03-23 15:40 ` Shakeel Butt
2023-03-23 15:42 ` Yosry Ahmed
2023-03-23 15:46 ` Shakeel Butt
2023-03-23 16:09 ` Shakeel Butt
2023-03-23 16:17 ` Yosry Ahmed
2023-03-23 16:29 ` Shakeel Butt
2023-03-23 16:36 ` Yosry Ahmed
2023-03-23 16:45 ` Shakeel Butt
2023-03-23 16:51 ` Yosry Ahmed
2023-03-23 19:09 ` Shakeel Butt
2023-03-23 17:33 ` Johannes Weiner
2023-03-23 18:09 ` Yosry Ahmed
2023-03-23 18:19 ` Johannes Weiner
2023-03-24 1:39 ` Tejun Heo
2023-03-24 7:22 ` Yosry Ahmed
2023-03-24 14:12 ` Waiman Long
2023-03-24 22:50 ` Yosry Ahmed
2023-03-25 1:54 ` Tejun Heo
2023-03-25 2:17 ` Yosry Ahmed
2023-03-25 4:30 ` Shakeel Butt
2023-03-25 4:37 ` Yosry Ahmed
2023-03-25 4:46 ` Shakeel Butt
2023-03-27 23:23 ` Yosry Ahmed
2023-03-29 18:53 ` Tejun Heo
2023-03-29 19:22 ` Hugh Dickins
2023-03-29 20:00 ` Tejun Heo
2023-03-29 20:38 ` Hugh Dickins
2023-03-30 4:26 ` Yosry Ahmed
2023-03-31 1:51 ` Tejun Heo
2023-03-23 4:00 ` [RFC PATCH 2/7] memcg: do not disable interrupts when holding stats_flush_lock Yosry Ahmed
2023-03-23 4:32 ` Shakeel Butt
2023-03-23 5:16 ` Yosry Ahmed
2023-03-23 4:00 ` [RFC PATCH 3/7] cgroup: rstat: remove cgroup_rstat_flush_irqsafe() Yosry Ahmed
2023-03-23 15:43 ` Johannes Weiner
2023-03-23 15:45 ` Yosry Ahmed
2023-03-23 4:00 ` [RFC PATCH 4/7] memcg: sleep during flushing stats in safe contexts Yosry Ahmed
2023-03-23 15:56 ` Johannes Weiner
2023-03-23 16:01 ` Yosry Ahmed
2023-03-23 17:27 ` Johannes Weiner
2023-03-23 18:07 ` Yosry Ahmed
2023-03-23 19:35 ` Shakeel Butt
2023-03-23 4:00 ` [RFC PATCH 5/7] vmscan: memcg: sleep when flushing stats during reclaim Yosry Ahmed
2023-03-23 4:00 ` [RFC PATCH 6/7] workingset: memcg: sleep when flushing stats in workingset_refault() Yosry Ahmed
2023-03-23 15:50 ` Johannes Weiner
2023-03-23 16:02 ` Yosry Ahmed
2023-03-23 16:00 ` Johannes Weiner
2023-03-23 16:02 ` Yosry Ahmed
2023-03-23 4:00 ` [RFC PATCH 7/7] memcg: do not modify rstat tree for zero updates Yosry Ahmed
2023-03-23 4:10 ` [RFC PATCH 0/7] Make rstat flushing IRQ and sleep friendly Shakeel Butt
2023-03-23 5:07 ` Yosry Ahmed
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=CAJD7tkY6Wf2OWja+f-JeFM5DdMCyLzbXxZ8KF0MjcYOKri-vtA@mail.gmail.com \
--to=yosryahmed@google.com \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=hannes@cmpxchg.org \
--cc=josef@toxicpanda.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan.x@bytedance.com \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=roman.gushchin@linux.dev \
--cc=shakeelb@google.com \
--cc=tj@kernel.org \
--cc=vasily.averin@linux.dev \
/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).