From: Rik van Riel <riel@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Luiz Capitulino <lcapitulino@redhat.com>,
Linux RT Users <linux-rt-users@vger.kernel.org>
Subject: Re: [patch 2/2] MM: allow per-cpu vmstat_threshold and vmstat_worker configuration
Date: Tue, 25 Apr 2017 15:29:06 -0400 [thread overview]
Message-ID: <1493148546.31102.1.camel@redhat.com> (raw)
In-Reply-To: <20170425135846.203663532@redhat.com>
On Tue, 2017-04-25 at 10:57 -0300, Marcelo Tosatti wrote:
> The per-CPU vmstat worker is a problem on -RT workloads (because
> ideally the CPU is entirely reserved for the -RT app, without
> interference). The worker transfers accumulated per-CPU
> vmstat counters to global counters.
>
> To resolve the problem, create two tunables:
>
> * Userspace configurable per-CPU vmstat threshold: by default the
> VM code calculates the size of the per-CPU vmstat arrays. This
> tunable allows userspace to configure the values.
>
> * Userspace configurable per-CPU vmstat worker: allow disabling
> the per-CPU vmstat worker.
>
> The patch below contains documentation which describes the tunables
> in more detail.
The documentation says what the tunables do, but
not how you should set them in different scenarios,
or why.
That could be a little more helpful to sysadmins.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Luiz Capitulino <lcapitulino@redhat.com>,
Linux RT Users <linux-rt-users@vger.kernel.org>
Subject: Re: [patch 2/2] MM: allow per-cpu vmstat_threshold and vmstat_worker configuration
Date: Tue, 25 Apr 2017 15:29:06 -0400 [thread overview]
Message-ID: <1493148546.31102.1.camel@redhat.com> (raw)
In-Reply-To: <20170425135846.203663532@redhat.com>
On Tue, 2017-04-25 at 10:57 -0300, Marcelo Tosatti wrote:
> The per-CPU vmstat worker is a problem on -RT workloads (because
> ideally the CPU is entirely reserved for the -RT app, without
> interference). The worker transfers accumulated per-CPUA
> vmstat counters to global counters.
>
> To resolve the problem, create two tunables:
>
> * Userspace configurable per-CPU vmstat threshold: by default theA
> VM code calculates the size of the per-CPU vmstat arrays. ThisA
> tunable allows userspace to configure the values.
>
> * Userspace configurable per-CPU vmstat worker: allow disabling
> the per-CPU vmstat worker.
>
> The patch below contains documentation which describes the tunables
> in more detail.
The documentation says what the tunables do, but
not how you should set them in different scenarios,
or why.
That could be a little more helpful to sysadmins.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Luiz Capitulino <lcapitulino@redhat.com>,
Linux RT Users <linux-rt-users@vger.kernel.org>
Subject: Re: [patch 2/2] MM: allow per-cpu vmstat_threshold and vmstat_worker configuration
Date: Tue, 25 Apr 2017 15:29:06 -0400 [thread overview]
Message-ID: <1493148546.31102.1.camel@redhat.com> (raw)
In-Reply-To: <20170425135846.203663532@redhat.com>
On Tue, 2017-04-25 at 10:57 -0300, Marcelo Tosatti wrote:
> The per-CPU vmstat worker is a problem on -RT workloads (because
> ideally the CPU is entirely reserved for the -RT app, without
> interference). The worker transfers accumulated per-CPU
> vmstat counters to global counters.
>
> To resolve the problem, create two tunables:
>
> * Userspace configurable per-CPU vmstat threshold: by default the
> VM code calculates the size of the per-CPU vmstat arrays. This
> tunable allows userspace to configure the values.
>
> * Userspace configurable per-CPU vmstat worker: allow disabling
> the per-CPU vmstat worker.
>
> The patch below contains documentation which describes the tunables
> in more detail.
The documentation says what the tunables do, but
not how you should set them in different scenarios,
or why.
That could be a little more helpful to sysadmins.
next prev parent reply other threads:[~2017-04-25 19:29 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-25 13:57 [patch 0/2] per-CPU vmstat thresholds and vmstat worker disablement Marcelo Tosatti
2017-04-25 13:57 ` Marcelo Tosatti
2017-04-25 13:57 ` [patch 1/2] MM: remove unused quiet_vmstat function Marcelo Tosatti
2017-04-25 13:57 ` Marcelo Tosatti
2017-04-25 13:57 ` [patch 2/2] MM: allow per-cpu vmstat_threshold and vmstat_worker configuration Marcelo Tosatti
2017-04-25 13:57 ` Marcelo Tosatti
2017-04-25 19:29 ` Rik van Riel [this message]
2017-04-25 19:29 ` Rik van Riel
2017-04-25 19:29 ` Rik van Riel
2017-04-25 19:36 ` Marcelo Tosatti
2017-04-25 19:36 ` Marcelo Tosatti
2017-04-25 19:36 ` Marcelo Tosatti
2017-05-02 14:28 ` Luiz Capitulino
2017-05-02 14:28 ` Luiz Capitulino
2017-05-02 16:52 ` Marcelo Tosatti
2017-05-02 16:52 ` Marcelo Tosatti
2017-05-02 17:15 ` Luiz Capitulino
2017-05-02 17:15 ` Luiz Capitulino
2017-05-02 17:21 ` Marcelo Tosatti
2017-05-02 17:21 ` Marcelo Tosatti
2017-05-02 17:21 ` Marcelo Tosatti
2017-05-11 15:37 ` Christoph Lameter
2017-05-11 15:37 ` Christoph Lameter
2017-05-12 12:27 ` Marcelo Tosatti
2017-05-12 12:27 ` Marcelo Tosatti
2017-05-12 15:11 ` Christoph Lameter
2017-05-12 15:11 ` Christoph Lameter
2017-05-12 15:40 ` Marcelo Tosatti
2017-05-12 15:40 ` Marcelo Tosatti
2017-05-12 16:03 ` Christoph Lameter
2017-05-12 16:03 ` Christoph Lameter
2017-05-12 16:07 ` Christoph Lameter
2017-05-12 16:07 ` Christoph Lameter
2017-05-12 16:19 ` Marcelo Tosatti
2017-05-12 16:19 ` Marcelo Tosatti
2017-05-12 16:57 ` Christoph Lameter
2017-05-12 16:57 ` Christoph Lameter
2017-05-15 19:15 ` Marcelo Tosatti
2017-05-15 19:15 ` Marcelo Tosatti
2017-05-16 13:37 ` Christoph Lameter
2017-05-16 13:37 ` Christoph Lameter
2017-05-19 14:34 ` Marcelo Tosatti
2017-05-19 14:34 ` Marcelo Tosatti
2017-05-19 17:13 ` Christoph Lameter
2017-05-19 17:13 ` Christoph Lameter
2017-05-19 17:49 ` Luiz Capitulino
2017-05-19 17:49 ` Luiz Capitulino
2017-05-22 16:35 ` Christoph Lameter
2017-05-22 16:35 ` Christoph Lameter
2017-05-25 19:35 ` Marcelo Tosatti
2017-05-25 19:35 ` Marcelo Tosatti
2017-05-25 19:35 ` Marcelo Tosatti
2017-05-26 3:24 ` Christoph Lameter
2017-05-26 3:24 ` Christoph Lameter
2017-05-26 19:09 ` Marcelo Tosatti
2017-05-26 19:09 ` Marcelo Tosatti
2017-05-30 18:17 ` Christoph Lameter
2017-05-30 18:17 ` Christoph Lameter
2017-07-10 15:05 ` Marcelo Tosatti
2017-07-10 15:05 ` Marcelo Tosatti
2017-05-20 8:26 ` Marcelo Tosatti
2017-05-20 8:26 ` Marcelo Tosatti
2017-05-22 16:38 ` Christoph Lameter
2017-05-22 16:38 ` Christoph Lameter
2017-05-22 21:13 ` Marcelo Tosatti
2017-05-22 21:13 ` 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=1493148546.31102.1.camel@redhat.com \
--to=riel@redhat.com \
--cc=lcapitulino@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rt-users@vger.kernel.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.