From: Hillf Danton <hdanton@sina.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: atomlin@atomlin.com, frederic@kernel.org,
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: Fri, 6 Jan 2023 23:01:54 +0800 [thread overview]
Message-ID: <20230106150154.4560-1-hdanton@sina.com> (raw)
In-Reply-To: <Y7gZNM9JHppbZ1Ed@tpad>
On 6 Jan 2023 09:51:00 -0300 Marcelo Tosatti <mtosatti@redhat.com>
> On Fri, Jan 06, 2023 at 08:12:44AM +0800, Hillf Danton wrote:
> >
> > Regression wrt V12 if timer is added on the CPU that is not doing HK_TYPE_TIMER?
>
> Before this change, the timer was managed (and queued on an isolated
> CPU) by vmstat_shepherd. Now it is managed (and queued) by the local
> CPU, so there is no regression.
Given vm stats folded when returning to userspace, queuing the delayed work
barely makes sense in the first place. If it can be canceled, queuing it burns
cycles with nothing earned. Otherwise vm stats got folded already.
Nor does shepherd even without delay. And the right thing is only make shepherd
leave isolated CPUs intact.
next prev parent reply other threads:[~2023-01-06 15:02 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 [this message]
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
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=20230106150154.4560-1-hdanton@sina.com \
--to=hdanton@sina.com \
--cc=atomlin@atomlin.com \
--cc=frederic@kernel.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox