linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Weisbecker <frederic@kernel.org>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: linux-kernel@vger.kernel.org, Christoph Lameter <cl@linux.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Juri Lelli <juri.lelli@redhat.com>, Nitesh Lal <nilal@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>
Subject: Re: [patch 0/5] optionally sync per-CPU vmstats counter on return to userspace
Date: Tue, 6 Jul 2021 15:09:25 +0200	[thread overview]
Message-ID: <20210706130925.GC107277@lothringen> (raw)
In-Reply-To: <20210702152816.GA4122@fuller.cnet>

On Fri, Jul 02, 2021 at 12:28:16PM -0300, Marcelo Tosatti wrote:
> 
> Hi Frederic,
> 
> On Fri, Jul 02, 2021 at 02:30:32PM +0200, Frederic Weisbecker wrote:
> > On Thu, Jul 01, 2021 at 06:03:36PM -0300, Marcelo Tosatti wrote:
> > > The logic to disable vmstat worker thread, when entering
> > > nohz full, does not cover all scenarios. For example, it is possible
> > > for the following to happen:
> > > 
> > > 1) enter nohz_full, which calls refresh_cpu_vm_stats, syncing the stats.
> > > 2) app runs mlock, which increases counters for mlock'ed pages.
> > > 3) start -RT loop
> > > 
> > > Since refresh_cpu_vm_stats from nohz_full logic can happen _before_
> > > the mlock, vmstat shepherd can restart vmstat worker thread on
> > > the CPU in question.
> > >  
> > > To fix this, optionally sync the vmstat counters when returning
> > > from userspace, controllable by a new "vmstat_sync" isolcpus
> > > flags (default off).
> > 
> > Wasn't the plan for such finegrained isolation features to do it at
> > the per task level using prctl()?
> 
> Yes, but its orthogonal: when we integrate the finegrained isolation
> interface, will be able to use this code (to sync vmstat counters
> on return to userspace) only when userspace informs that it has entered
> isolated mode, so you don't incur the performance penalty of frequent
> vmstat counter writes when not using isolated apps.
> 
> This is what the full task isolation task patchset mode is doing
> as well (CC'ing Alex BTW).

Right there can be two ways:

* A prctl request to sync vmstat only on exit from that prctl
* A prctl request to sync vmstat on all subsequent exit from
  kernel space.

> 
> This will require modifying applications (and the new kernel with the
> exposed interface).
> 
> But there is demand for fixing this now, for currently existing
> binary only applications.

I would agree if it were a regression but it's not. It's merely
a new feature and we don't want to rush on a broken interface.

And I suspect some other people won't like much a new extension
to isolcpus.

  reply	other threads:[~2021-07-06 13:09 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-01 21:03 [patch 0/5] optionally sync per-CPU vmstats counter on return to userspace Marcelo Tosatti
2021-07-01 21:03 ` [patch 1/5] sched: isolation: introduce vmstat_sync isolcpu flags Marcelo Tosatti
2021-07-01 21:03 ` [patch 2/5] common entry: add hook for isolation to __syscall_exit_to_user_mode_work Marcelo Tosatti
2021-07-01 21:03 ` [patch 3/5] mm: vmstat: optionally flush per-CPU vmstat counters on return to userspace Marcelo Tosatti
2021-07-01 23:11   ` kernel test robot
2021-07-02  6:50   ` kernel test robot
2021-07-01 21:03 ` [patch 4/5] mm: vmstat: move need_update Marcelo Tosatti
2021-07-01 21:03 ` [patch 5/5] mm: vmstat_refresh: avoid queueing work item if cpu stats are clean Marcelo Tosatti
2021-07-02  4:10   ` kernel test robot
2021-07-02  4:43   ` kernel test robot
2021-07-02  8:00 ` [patch 0/5] optionally sync per-CPU vmstats counter on return to userspace Christoph Lameter
2021-07-02 11:52   ` Marcelo Tosatti
2021-07-02 11:59   ` Marcelo Tosatti
2021-07-05 14:26     ` Christoph Lameter
2021-07-05 14:45       ` Marcelo Tosatti
2021-07-02 12:30 ` Frederic Weisbecker
2021-07-02 15:28   ` Marcelo Tosatti
2021-07-06 13:09     ` Frederic Weisbecker [this message]
2021-07-06 14:05       ` Marcelo Tosatti
2021-07-06 14:09         ` Marcelo Tosatti
2021-07-06 14:17           ` Marcelo Tosatti
2021-07-06 16:15           ` Peter Zijlstra
2021-07-06 16:53             ` Marcelo Tosatti

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=20210706130925.GC107277@lothringen \
    --to=frederic@kernel.org \
    --cc=cl@linux.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=nilal@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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).