From: Frederic Weisbecker <frederic@kernel.org>
To: Hillf Danton <hdanton@sina.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
atomlin@atomlin.com, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH v13 3/6] mm/vmstat: manage per-CPU stats from CPU context when NOHZ full
Date: Tue, 10 Jan 2023 17:12:22 +0100 [thread overview]
Message-ID: <Y72OZn6mULPX4xk8@lothringen> (raw)
In-Reply-To: <20230110151901.402-1-hdanton@sina.com>
On Tue, Jan 10, 2023 at 11:19:01PM +0800, Hillf Danton wrote:
> On Tue, 10 Jan 2023 08:50:28 -0300 Marcelo Tosatti <mtosatti@redhat.com>
> > On Tue, Jan 10, 2023 at 10:43:56AM +0800, Hillf Danton wrote:
> > > On 9 Jan 2023 11:12:49 -0300 Marcelo Tosatti <mtosatti@redhat.com>
> > > >
> > > > Yes, but if you do not return to userspace, then the per-CPU vm
> > > > statistics can be dirty indefinitely.
> > >
> > > Could you specify the reasons for failing to return to userspace,
> > > given it is undesired intereference for the shepherd to queue work
> > > on the isolated CPUs.
> >
> > Any system call that takes longer than the threshold to sync vmstats.
>
> Which ones?
>
> If schedule() occurs during syscall because of acquiring mutex for instance
> then anything on the isolated runqueue, including workqueue worker shepherd
> wakes up, can burn CPU cycles without undesired intereference produced.
The above confuses me. How others tasks would help with syscalls that take too long too
service?
> >
> > Or a long running kernel thread, for example:
>
> It is a buggyyyy example.
> >
> > https://stackoverflow.com/questions/65111483/long-running-kthread-and-synchronize-net
I can imagine a CPU spending most of its time processing networking packets
through interrupts/softirq within ksoftirqd/NAPI while another CPU process
these packets in userspace.
In this case the CPU handling the kernel part can theoretically never go to
idle/user. nohz_full isn't optimized toward such job but there is nothing
to prevent it from doing such job.
Thanks.
next prev parent reply other threads:[~2023-01-10 16:12 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-05 12:52 [PATCH v13 0/6] Ensure quiet_vmstat() is called when returning to userpace and when idle tick is stopped Marcelo Tosatti
2023-01-05 12:52 ` [PATCH v13 1/6] mm/vmstat: Add CPU-specific variable to track a vmstat discrepancy Marcelo Tosatti
2023-01-10 11:58 ` Christoph Lameter
2023-01-10 12:12 ` Frederic Weisbecker
2023-01-05 12:52 ` [PATCH v13 2/6] mm/vmstat: Use vmstat_dirty to track CPU-specific vmstat discrepancies Marcelo Tosatti
2023-01-10 12:06 ` Christoph Lameter
2023-01-10 12:18 ` Frederic Weisbecker
2023-01-10 13:39 ` Christoph Lameter
2023-01-10 20:09 ` Marcelo Tosatti
2023-01-11 8:42 ` Christoph Lameter
2023-01-11 17:07 ` Marcelo Tosatti
2023-01-16 9:51 ` Christoph Lameter
2023-01-16 16:11 ` Marcelo Tosatti
2023-01-17 12:52 ` Christoph Lameter
2023-01-05 12:52 ` [PATCH v13 3/6] mm/vmstat: manage per-CPU stats from CPU context when NOHZ full Marcelo Tosatti
2023-01-05 12:52 ` [PATCH v13 4/6] tick/nohz_full: Ensure quiet_vmstat() is called on exit to user-mode when the idle tick is stopped Marcelo Tosatti
2023-01-05 12:52 ` [PATCH v13 5/6] tick/sched: Ensure quiet_vmstat() is called when the idle tick was stopped too Marcelo Tosatti
2023-01-05 12:52 ` [PATCH v13 6/6] mm/vmstat: avoid queueing work item if cpu stats are clean Marcelo Tosatti
[not found] ` <20230106001244.4463-1-hdanton@sina.com>
2023-01-06 12:51 ` [PATCH v13 3/6] mm/vmstat: manage per-CPU stats from CPU context when NOHZ full Marcelo Tosatti
2023-01-06 15:01 ` Hillf Danton
2023-01-06 18:16 ` Marcelo Tosatti
2023-01-07 0:15 ` Hillf Danton
2023-01-09 14:12 ` Marcelo Tosatti
2023-01-10 2:43 ` Hillf Danton
2023-01-10 11:50 ` Marcelo Tosatti
2023-01-10 15:19 ` Hillf Danton
2023-01-10 16:12 ` Frederic Weisbecker [this message]
2023-01-10 23:58 ` Hillf Danton
2023-01-11 0:09 ` Frederic Weisbecker
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=Y72OZn6mULPX4xk8@lothringen \
--to=frederic@kernel.org \
--cc=atomlin@atomlin.com \
--cc=hdanton@sina.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mtosatti@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.