All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-kernel@vger.kernel.org, jack@suse.cz, hch@infradead.org,
	hannes@cmpxchg.org, linux-fsdevel@vger.kernel.org,
	vgoyal@redhat.com, lizefan@huawei.com, cgroups@vger.kernel.org,
	linux-mm@kvack.org, mhocko@suse.cz, clm@fb.com,
	fengguang.wu@intel.com, david@fromorbit.com, gthelen@google.com,
	Vladimir Davydov <vdavydov@parallels.com>
Subject: Re: [PATCH 18/18] mm: vmscan: remove memcg stalling on writeback pages during direct reclaim
Date: Mon, 23 Mar 2015 01:27:22 -0400	[thread overview]
Message-ID: <20150323052722.GB8991@htj.duckdns.org> (raw)
In-Reply-To: <1427087267-16592-19-git-send-email-tj@kernel.org>

On Mon, Mar 23, 2015 at 01:07:47AM -0400, Tejun Heo wrote:
> Because writeback wasn't cgroup aware before, the usual dirty
> throttling mechanism in balance_dirty_pages() didn't work for
> processes under memcg limit.  The writeback path didn't know how much
> memory is available or how fast the dirty pages are being written out
> for a given memcg and balance_dirty_pages() didn't have any measure of
> IO back pressure for the memcg.
> 
> To work around the issue, memcg implemented an ad-hoc dirty throttling
> mechanism in the direct reclaim path by stalling on pages under
> writeback which are encountered during direct reclaim scan.  This is
> rather ugly and crude - none of the configurability, fairness, or
> bandwidth-proportional distribution of the normal path.
> 
> The previous patches implemented proper memcg aware dirty throttling
> and the ad-hoc mechanism is no longer necessary.  Remove it.

Oops, just realized that this can't be removed, at least yet.
!unified path still depends on it.  I'll update the patch to disable
these checks only on the unified hierarchy.

Thanks.

-- 
tejun

WARNING: multiple messages have this Message-ID (diff)
From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-kernel@vger.kernel.org, jack@suse.cz, hch@infradead.org,
	hannes@cmpxchg.org, linux-fsdevel@vger.kernel.org,
	vgoyal@redhat.com, lizefan@huawei.com, cgroups@vger.kernel.org,
	linux-mm@kvack.org, mhocko@suse.cz, clm@fb.com,
	fengguang.wu@intel.com, david@fromorbit.com, gthelen@google.com,
	Vladimir Davydov <vdavydov@parallels.com>
Subject: Re: [PATCH 18/18] mm: vmscan: remove memcg stalling on writeback pages during direct reclaim
Date: Mon, 23 Mar 2015 01:27:22 -0400	[thread overview]
Message-ID: <20150323052722.GB8991@htj.duckdns.org> (raw)
In-Reply-To: <1427087267-16592-19-git-send-email-tj@kernel.org>

On Mon, Mar 23, 2015 at 01:07:47AM -0400, Tejun Heo wrote:
> Because writeback wasn't cgroup aware before, the usual dirty
> throttling mechanism in balance_dirty_pages() didn't work for
> processes under memcg limit.  The writeback path didn't know how much
> memory is available or how fast the dirty pages are being written out
> for a given memcg and balance_dirty_pages() didn't have any measure of
> IO back pressure for the memcg.
> 
> To work around the issue, memcg implemented an ad-hoc dirty throttling
> mechanism in the direct reclaim path by stalling on pages under
> writeback which are encountered during direct reclaim scan.  This is
> rather ugly and crude - none of the configurability, fairness, or
> bandwidth-proportional distribution of the normal path.
> 
> The previous patches implemented proper memcg aware dirty throttling
> and the ad-hoc mechanism is no longer necessary.  Remove it.

Oops, just realized that this can't be removed, at least yet.
!unified path still depends on it.  I'll update the patch to disable
these checks only on the unified hierarchy.

Thanks.

-- 
tejun

--
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>

  reply	other threads:[~2015-03-23  5:27 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-23  5:07 [PATCHSET 2/3 block/for-4.1/core] writeback: cgroup writeback backpressure propagation Tejun Heo
2015-03-23  5:07 ` Tejun Heo
2015-03-23  5:07 ` [PATCH 01/18] memcg: make mem_cgroup_read_{stat|event}() iterate possible cpus instead of online Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-25 22:39   ` [PATCH 1.5/18] writeback: clean up wb_dirty_limit() Tejun Heo
2015-03-25 22:39     ` Tejun Heo
2015-03-25 22:39     ` Tejun Heo
2015-03-25 22:39     ` Tejun Heo
2015-03-23  5:07 ` [PATCH 02/18] writeback: reorganize [__]wb_update_bandwidth() Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 03/18] writeback: implement wb_domain Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 04/18] writeback: move global_dirty_limit into wb_domain Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 05/18] writeback: consolidate dirty throttle parameters into dirty_throttle_control Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 06/18] writeback: add dirty_throttle_control->wb_bg_thresh Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 07/18] writeback: make __wb_dirty_limit() take dirty_throttle_control Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-25 22:42   ` [PATCH v2 07/18] writeback: make __wb_calc_thresh() " Tejun Heo
2015-03-25 22:42     ` Tejun Heo
2015-03-25 22:42     ` Tejun Heo
2015-03-25 22:42     ` Tejun Heo
2015-03-23  5:07 ` [PATCH 08/18] writeback: add dirty_throttle_control->pos_ratio Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 09/18] writeback: add dirty_throttle_control->wb_completions Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 10/18] writeback: add dirty_throttle_control->dom Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 11/18] writeback: make __wb_writeout_inc() and hard_dirty_limit() take wb_domaas a parameter Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 12/18] writeback: separate out domain_dirty_limits() Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 13/18] writeback: move over_bground_thresh() to mm/page-writeback.c Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 14/18] writeback: update wb_over_bg_thresh() to use wb_domain aware operations Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 15/18] writeback: implement memcg wb_domain Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 16/18] writeback: reset wb_domain->dirty_limit[_tstmp] when memcg domain size changes Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 17/18] writeback: implement memcg writeback domain based throttling Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:07 ` [PATCH 18/18] mm: vmscan: remove memcg stalling on writeback pages during direct reclaim Tejun Heo
2015-03-23  5:07   ` Tejun Heo
2015-03-23  5:27   ` Tejun Heo [this message]
2015-03-23  5:27     ` Tejun Heo
2015-03-25 22:26   ` [PATCH v2 18/18] mm: vmscan: disable memcg direct reclaim stalling if cgroup writeback support is in use Tejun Heo
2015-03-25 22:26     ` Tejun Heo
2015-03-25 22:26     ` Tejun Heo
2015-03-25 22:26     ` Tejun Heo

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=20150323052722.GB8991@htj.duckdns.org \
    --to=tj@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=clm@fb.com \
    --cc=david@fromorbit.com \
    --cc=fengguang.wu@intel.com \
    --cc=gthelen@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lizefan@huawei.com \
    --cc=mhocko@suse.cz \
    --cc=vdavydov@parallels.com \
    --cc=vgoyal@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.