From: Vladimir Davydov <vdavydov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
To: Michel Lespinasse <walken-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: Michal Hocko <mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Andrew Morton
<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
Andres Lagar-Cavilla
<andreslc-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
Minchan Kim <minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Raghavendra K T
<raghavendra.kt-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>,
Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
David Rientjes <rientjes-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
Pavel Emelyanov <xemul-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>,
Cyrill Gorcunov
<gorcunov-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>,
Jonathan Corbet <corbet-T1hC0tSOHrs@public.gmane.org>,
linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH -mm v9 0/8] idle memory tracking
Date: Wed, 29 Jul 2015 18:31:35 +0300 [thread overview]
Message-ID: <20150729153135.GW8100@esperanza> (raw)
In-Reply-To: <CANN689Euq3Y-CHQo8q88vzFAYZX4S6rK+rZRfbuSKfS74u=gcg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Wed, Jul 29, 2015 at 08:08:22AM -0700, Michel Lespinasse wrote:
> On Wed, Jul 29, 2015 at 7:45 AM, Vladimir Davydov <vdavydov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
> wrote:
> > Page table scan approach has the inherent problem - it ignores unmapped
> > page cache. If a workload does a lot of read/write or map-access-unmap
> > operations, we won't be able to even roughly estimate its wss.
>
> You can catch that in mark_page_accessed on those paths, though.
Actually, the problem here is how to find an unmapped page cache page
*to mark it idle*, not to mark it accessed.
Thanks,
Vladimir
WARNING: multiple messages have this Message-ID (diff)
From: Vladimir Davydov <vdavydov@parallels.com>
To: Michel Lespinasse <walken@google.com>
Cc: Michal Hocko <mhocko@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Andres Lagar-Cavilla <andreslc@google.com>,
Minchan Kim <minchan@kernel.org>,
Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Greg Thelen <gthelen@google.com>,
David Rientjes <rientjes@google.com>,
Pavel Emelyanov <xemul@parallels.com>,
Cyrill Gorcunov <gorcunov@openvz.org>,
Jonathan Corbet <corbet@lwn.net>,
linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
linux-mm@kvack.org, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH -mm v9 0/8] idle memory tracking
Date: Wed, 29 Jul 2015 18:31:35 +0300 [thread overview]
Message-ID: <20150729153135.GW8100@esperanza> (raw)
In-Reply-To: <CANN689Euq3Y-CHQo8q88vzFAYZX4S6rK+rZRfbuSKfS74u=gcg@mail.gmail.com>
On Wed, Jul 29, 2015 at 08:08:22AM -0700, Michel Lespinasse wrote:
> On Wed, Jul 29, 2015 at 7:45 AM, Vladimir Davydov <vdavydov@parallels.com>
> wrote:
> > Page table scan approach has the inherent problem - it ignores unmapped
> > page cache. If a workload does a lot of read/write or map-access-unmap
> > operations, we won't be able to even roughly estimate its wss.
>
> You can catch that in mark_page_accessed on those paths, though.
Actually, the problem here is how to find an unmapped page cache page
*to mark it idle*, not to mark it accessed.
Thanks,
Vladimir
--
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: Vladimir Davydov <vdavydov@parallels.com>
To: Michel Lespinasse <walken@google.com>
Cc: Michal Hocko <mhocko@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Andres Lagar-Cavilla <andreslc@google.com>,
Minchan Kim <minchan@kernel.org>,
Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Greg Thelen <gthelen@google.com>,
David Rientjes <rientjes@google.com>,
"Pavel Emelyanov" <xemul@parallels.com>,
Cyrill Gorcunov <gorcunov@openvz.org>,
Jonathan Corbet <corbet@lwn.net>, <linux-api@vger.kernel.org>,
<linux-doc@vger.kernel.org>, <linux-mm@kvack.org>,
<cgroups@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH -mm v9 0/8] idle memory tracking
Date: Wed, 29 Jul 2015 18:31:35 +0300 [thread overview]
Message-ID: <20150729153135.GW8100@esperanza> (raw)
In-Reply-To: <CANN689Euq3Y-CHQo8q88vzFAYZX4S6rK+rZRfbuSKfS74u=gcg@mail.gmail.com>
On Wed, Jul 29, 2015 at 08:08:22AM -0700, Michel Lespinasse wrote:
> On Wed, Jul 29, 2015 at 7:45 AM, Vladimir Davydov <vdavydov@parallels.com>
> wrote:
> > Page table scan approach has the inherent problem - it ignores unmapped
> > page cache. If a workload does a lot of read/write or map-access-unmap
> > operations, we won't be able to even roughly estimate its wss.
>
> You can catch that in mark_page_accessed on those paths, though.
Actually, the problem here is how to find an unmapped page cache page
*to mark it idle*, not to mark it accessed.
Thanks,
Vladimir
next prev parent reply other threads:[~2015-07-29 15:31 UTC|newest]
Thread overview: 135+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-19 12:31 [PATCH -mm v9 0/8] idle memory tracking Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 1/8] memcg: add page_cgroup_ino helper Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
2015-07-22 9:21 ` Vladimir Davydov
2015-07-22 9:21 ` Vladimir Davydov
2015-07-22 9:21 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 2/8] hwpoison: use page_cgroup_ino for filtering by memcg Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
[not found] ` <20150721163412.1b44e77f5ac3b742734d1ce6-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2015-07-22 9:45 ` Vladimir Davydov
2015-07-22 9:45 ` Vladimir Davydov
2015-07-22 9:45 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 3/8] memcg: zap try_get_mem_cgroup_from_page Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 4/8] proc: add kpagecgroup file Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
[not found] ` <20150721163433.618855e1f61536a09dfac30b-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2015-07-22 10:33 ` Vladimir Davydov
2015-07-22 10:33 ` Vladimir Davydov
2015-07-22 10:33 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 5/8] mmu-notifier: add clear_young callback Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-20 18:34 ` Andres Lagar-Cavilla
2015-07-21 8:51 ` Vladimir Davydov
2015-07-21 8:51 ` Vladimir Davydov
2015-07-22 16:33 ` Vladimir Davydov
2015-07-22 16:33 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 6/8] proc: add kpageidle file Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
[not found] ` <20150721163452.c1e4075a2b193bcd325fad56-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2015-07-22 15:20 ` Vladimir Davydov
2015-07-22 15:20 ` Vladimir Davydov
2015-07-22 15:20 ` Vladimir Davydov
[not found] ` <d7a78b72053cf529c0c9ff6cbc02ffbb3d58fe35.1437303956.git.vdavydov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2015-07-24 14:08 ` Paul Gortmaker
2015-07-24 14:08 ` Paul Gortmaker
2015-07-24 14:08 ` Paul Gortmaker
[not found] ` <CAP=VYLqiNfQJ6oyQg2GszeHwdOmeY_uD3XPvw=++weJOKdx4_g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-07-24 14:17 ` Vladimir Davydov
2015-07-24 14:17 ` Vladimir Davydov
2015-07-24 14:17 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 7/8] proc: export idle flag via kpageflags Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
2015-07-21 23:35 ` Andrew Morton
2015-07-21 23:35 ` Andrew Morton
[not found] ` <20150721163500.528bd39bbbc71abc3c8d429b-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2015-07-22 16:25 ` Vladimir Davydov
2015-07-22 16:25 ` Vladimir Davydov
2015-07-22 16:25 ` Vladimir Davydov
2015-07-22 19:44 ` Andrew Morton
2015-07-22 19:44 ` Andrew Morton
2015-07-22 19:44 ` Andrew Morton
2015-07-22 20:46 ` Andres Lagar-Cavilla
2015-07-23 7:57 ` Vladimir Davydov
2015-07-23 7:57 ` Vladimir Davydov
2015-07-23 7:57 ` Vladimir Davydov
2015-07-19 12:31 ` [PATCH -mm v9 8/8] proc: add cond_resched to /proc/kpage* read/write loop Vladimir Davydov
2015-07-19 12:31 ` Vladimir Davydov
[not found] ` <cover.1437303956.git.vdavydov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2015-07-19 12:37 ` [PATCH -mm v9 0/8] idle memory tracking Vladimir Davydov
2015-07-19 12:37 ` Vladimir Davydov
2015-07-19 12:37 ` Vladimir Davydov
2015-07-21 21:39 ` Andres Lagar-Cavilla
2015-07-21 23:34 ` Andrew Morton
2015-07-21 23:34 ` Andrew Morton
2015-07-22 16:23 ` Vladimir Davydov
2015-07-22 16:23 ` Vladimir Davydov
2015-07-22 16:23 ` Vladimir Davydov
2015-07-25 16:24 ` Vladimir Davydov
2015-07-25 16:24 ` Vladimir Davydov
2015-07-25 16:24 ` Vladimir Davydov
2015-07-27 19:18 ` Kees Cook
2015-07-27 19:18 ` Kees Cook
2015-07-27 19:25 ` Andrew Morton
2015-07-27 19:25 ` Andrew Morton
2015-07-29 12:36 ` Michal Hocko
2015-07-29 12:36 ` Michal Hocko
[not found] ` <20150729123629.GI15801-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2015-07-29 13:59 ` Vladimir Davydov
2015-07-29 13:59 ` Vladimir Davydov
2015-07-29 13:59 ` Vladimir Davydov
2015-07-29 14:12 ` Michel Lespinasse
[not found] ` <CANN689HJX2ZL891uOd8TW9ct4PNH9d5odQZm86WMxkpkCWhA-w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-07-29 14:13 ` Michel Lespinasse
2015-07-29 14:13 ` Michel Lespinasse
2015-07-29 14:13 ` Michel Lespinasse
2015-07-29 14:45 ` Vladimir Davydov
2015-07-29 14:45 ` Vladimir Davydov
2015-07-29 14:45 ` Vladimir Davydov
2015-07-29 15:08 ` Michel Lespinasse
[not found] ` <CANN689Euq3Y-CHQo8q88vzFAYZX4S6rK+rZRfbuSKfS74u=gcg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-07-29 15:31 ` Vladimir Davydov [this message]
2015-07-29 15:31 ` Vladimir Davydov
2015-07-29 15:31 ` Vladimir Davydov
2015-07-29 15:34 ` Michel Lespinasse
2015-07-29 15:08 ` Michal Hocko
2015-07-29 15:08 ` Michal Hocko
[not found] ` <20150729150855.GM15801-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2015-07-29 15:36 ` Vladimir Davydov
2015-07-29 15:36 ` Vladimir Davydov
2015-07-29 15:36 ` Vladimir Davydov
2015-07-29 15:58 ` Michal Hocko
2015-07-29 15:58 ` Michal Hocko
2015-07-29 14:26 ` Michal Hocko
2015-07-29 14:26 ` Michal Hocko
2015-07-29 15:28 ` Vladimir Davydov
2015-07-29 15:28 ` Vladimir Davydov
2015-07-29 15:47 ` Michal Hocko
2015-07-29 15:47 ` Michal Hocko
2015-07-29 15:47 ` Michal Hocko
[not found] ` <20150729154718.GN15801-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2015-07-29 16:29 ` Vladimir Davydov
2015-07-29 16:29 ` Vladimir Davydov
2015-07-29 16:29 ` Vladimir Davydov
2015-07-29 21:30 ` Andrew Morton
2015-07-29 21:30 ` Andrew Morton
2015-07-29 21:30 ` Andrew Morton
2015-07-30 9:12 ` Vladimir Davydov
2015-07-30 9:12 ` Vladimir Davydov
2015-07-30 13:01 ` Vladimir Davydov
2015-07-30 13:01 ` Vladimir Davydov
2015-07-30 13:01 ` Vladimir Davydov
2015-07-31 9:34 ` Vladimir Davydov
2015-07-31 9:34 ` Vladimir Davydov
2015-07-31 9:34 ` Vladimir Davydov
2015-07-30 9:07 ` Michal Hocko
2015-07-30 9:07 ` Michal Hocko
2015-07-30 9:07 ` Michal Hocko
[not found] ` <20150730090708.GE9387-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2015-07-30 9:31 ` Vladimir Davydov
2015-07-30 9:31 ` Vladimir Davydov
2015-07-30 9:31 ` Vladimir Davydov
2015-07-29 15:55 ` Andres Lagar-Cavilla
2015-07-29 15:55 ` Andres Lagar-Cavilla
[not found] ` <CAJu=L59RdowYjTyVM0Vhz79A4d=d8=ZmU7PB59CmEj5B0_c48Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-07-29 16:37 ` Vladimir Davydov
2015-07-29 16:37 ` Vladimir Davydov
2015-07-29 16:37 ` Vladimir Davydov
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=20150729153135.GW8100@esperanza \
--to=vdavydov-bzqdu9zft3wakbo8gow8eq@public.gmane.org \
--cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
--cc=andreslc-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=corbet-T1hC0tSOHrs@public.gmane.org \
--cc=gorcunov-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org \
--cc=gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org \
--cc=linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
--cc=mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=raghavendra.kt-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org \
--cc=rientjes-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=walken-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=xemul-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org \
/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.