linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alex Shi <alex.shi@linux.alibaba.com>
To: akpm@linux-foundation.org, mgorman@techsingularity.net,
	tj@kernel.org, hughd@google.com, khlebnikov@yandex-team.ru,
	daniel.m.jordan@oracle.com, willy@infradead.org,
	hannes@cmpxchg.org, lkp@intel.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	shakeelb@google.com, iamjoonsoo.kim@lge.com,
	richard.weiyang@gmail.com, kirill@shutemov.name,
	alexander.duyck@gmail.com, rong.a.chen@intel.com,
	mhocko@suse.com, vdavydov.dev@gmail.com, shy828301@gmail.com
Subject: [PATCH v20 00/20] per memcg lru lock
Date: Thu, 29 Oct 2020 18:44:45 +0800	[thread overview]
Message-ID: <1603968305-8026-1-git-send-email-alex.shi@linux.alibaba.com> (raw)

This version just a rebase on v5.10-rc1. and moves the lru_lock position
down after lists[] in lruvec, which resolves a fio.read regression that
revealed by Rong Chen -- Intel LKP.

Many thanks for line by line review by Hugh Dickins and Alexander Duyck.

So now this patchset includes 3 parts:
1, some code cleanup and minimum optimization as a preparation. 
2, use TestCleanPageLRU as page isolation's precondition.
3, replace per node lru_lock with per memcg per node lru_lock.

Current lru_lock is one for each of node, pgdat->lru_lock, that guard for
lru lists, but now we had moved the lru lists into memcg for long time. Still
using per node lru_lock is clearly unscalable, pages on each of memcgs have
to compete each others for a whole lru_lock. This patchset try to use per
lruvec/memcg lru_lock to repleace per node lru lock to guard lru lists, make
it scalable for memcgs and get performance gain.

Currently lru_lock still guards both lru list and page's lru bit, that's ok.
but if we want to use specific lruvec lock on the page, we need to pin down
the page's lruvec/memcg during locking. Just taking lruvec lock first may be
undermined by the page's memcg charge/migration. To fix this problem, we could
take out the page's lru bit clear and use it as pin down action to block the
memcg changes. That's the reason for new atomic func TestClearPageLRU.
So now isolating a page need both actions: TestClearPageLRU and hold the
lru_lock.

The typical usage of this is isolate_migratepages_block() in compaction.c
we have to take lru bit before lru lock, that serialized the page isolation
in memcg page charge/migration which will change page's lruvec and new 
lru_lock in it.

The above solution suggested by Johannes Weiner, and based on his new memcg 
charge path, then have this patchset. (Hugh Dickins tested and contributed much
code from compaction fix to general code polish, thanks a lot!).

Daniel Jordan's testing show 62% improvement on modified readtwice case
on his 2P * 10 core * 2 HT broadwell box on v18, which has no much different
with this v20.
https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/

Thanks Hugh Dickins and Konstantin Khlebnikov, they both brought this
idea 8 years ago, and others who give comments as well: Daniel Jordan, 
Mel Gorman, Shakeel Butt, Matthew Wilcox, Alexander Duyck etc.

Thanks for Testing support from Intel 0day and Rong Chen, Fengguang Wu,
and Yun Wang. Hugh Dickins also shared his kbuild-swap case. Thanks!

Alex Shi (17):
  mm/memcg: warning on !memcg after readahead page charged
  mm/memcg: bail early from swap accounting if memcg disabled
  mm/thp: move lru_add_page_tail func to huge_memory.c
  mm/thp: use head for head page in lru_add_page_tail
  mm/thp: Simplify lru_add_page_tail()
  mm/thp: narrow lru locking
  mm/vmscan: remove unnecessary lruvec adding
  mm/memcg: add debug checking in lock_page_memcg
  mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn
  mm/lru: move lock into lru_note_cost
  mm/vmscan: remove lruvec reget in move_pages_to_lru
  mm/mlock: remove lru_lock on TestClearPageMlocked
  mm/mlock: remove __munlock_isolate_lru_page
  mm/lru: introduce TestClearPageLRU
  mm/compaction: do page isolation first in compaction
  mm/swap.c: serialize memcg changes in pagevec_lru_move_fn
  mm/lru: replace pgdat lru_lock with lruvec lock

Alexander Duyck (1):
  mm/lru: introduce the relock_page_lruvec function

Hugh Dickins (2):
  mm: page_idle_get_page() does not need lru_lock
  mm/lru: revise the comments of lru_lock

 Documentation/admin-guide/cgroup-v1/memcg_test.rst |  15 +-
 Documentation/admin-guide/cgroup-v1/memory.rst     |  21 +--
 Documentation/trace/events-kmem.rst                |   2 +-
 Documentation/vm/unevictable-lru.rst               |  22 +--
 include/linux/memcontrol.h                         | 110 +++++++++++
 include/linux/mm_types.h                           |   2 +-
 include/linux/mmdebug.h                            |  13 ++
 include/linux/mmzone.h                             |   6 +-
 include/linux/page-flags.h                         |   1 +
 include/linux/swap.h                               |   4 +-
 mm/compaction.c                                    |  94 +++++++---
 mm/filemap.c                                       |   4 +-
 mm/huge_memory.c                                   |  45 +++--
 mm/memcontrol.c                                    |  85 ++++++++-
 mm/mlock.c                                         |  63 ++-----
 mm/mmzone.c                                        |   1 +
 mm/page_alloc.c                                    |   1 -
 mm/page_idle.c                                     |   4 -
 mm/rmap.c                                          |   4 +-
 mm/swap.c                                          | 199 ++++++++------------
 mm/vmscan.c                                        | 203 +++++++++++----------
 mm/workingset.c                                    |   2 -
 22 files changed, 523 insertions(+), 378 deletions(-)

-- 
1.8.3.1


             reply	other threads:[~2020-10-29 10:45 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-29 10:44 Alex Shi [this message]
2020-10-29 10:44 ` [PATCH v20 01/20] mm/memcg: warning on !memcg after readahead page charged Alex Shi
2020-10-29 13:43   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 02/20] mm/memcg: bail early from swap accounting if memcg disabled Alex Shi
2020-10-29 13:46   ` Johannes Weiner
2020-10-30  2:27     ` Alex Shi
2020-10-30 14:04       ` Johannes Weiner
2020-10-31  1:13         ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 03/20] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-10-29 13:47   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 04/20] mm/thp: use head for head page in lru_add_page_tail Alex Shi
2020-10-29 13:50   ` Johannes Weiner
2020-10-30  2:46     ` Alex Shi
2020-10-30 13:52       ` Johannes Weiner
2020-10-31  1:14         ` Alex Shi
2020-11-02 16:03       ` Matthew Wilcox
2020-11-03  2:43         ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 05/20] mm/thp: Simplify lru_add_page_tail() Alex Shi
2020-10-29 14:00   ` Johannes Weiner
2020-10-30  2:48   ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 06/20] mm/thp: narrow lru locking Alex Shi
2020-10-29 10:44 ` [PATCH v20 07/20] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-11-02 14:20   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 08/20] mm: page_idle_get_page() does not need lru_lock Alex Shi
2020-11-02 14:41   ` Johannes Weiner
2020-11-02 14:49     ` Matthew Wilcox
2020-11-02 20:20       ` Johannes Weiner
2020-11-04 11:27         ` Alex Shi
2020-11-04 17:46           ` Johannes Weiner
2020-11-05  4:52             ` Alex Shi
2020-11-05  4:57               ` Matthew Wilcox
2020-11-05  5:03                 ` Alex Shi
2020-11-05 15:36                   ` Johannes Weiner
2020-11-05 15:43                     ` Matthew Wilcox
2020-11-06  1:11                     ` Alex Shi
2020-11-11  7:27     ` Hugh Dickins
2020-10-29 10:44 ` [PATCH v20 09/20] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-11-02 14:45   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 10/20] mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-11-02 14:48   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 11/20] mm/lru: move lock into lru_note_cost Alex Shi
2020-10-29 13:42   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 12/20] mm/vmscan: remove lruvec reget in move_pages_to_lru Alex Shi
2020-11-02 14:52   ` Johannes Weiner
2020-11-03  2:51     ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 13/20] mm/mlock: remove lru_lock on TestClearPageMlocked Alex Shi
2020-11-02 14:55   ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 14/20] mm/mlock: remove __munlock_isolate_lru_page Alex Shi
2020-11-02 14:56   ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 15/20] mm/lru: introduce TestClearPageLRU Alex Shi
2020-11-02 15:10   ` Johannes Weiner
2020-11-03  3:02     ` Alex Shi
2020-10-29 10:45 ` [PATCH v20 16/20] mm/compaction: do page isolation first in compaction Alex Shi
2020-11-02 15:18   ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 17/20] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn Alex Shi
2020-11-02 15:20   ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 18/20] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-10-30  2:49   ` Alex Shi
2020-11-02 20:41     ` Johannes Weiner
2020-11-03  4:58       ` Alex Shi
2020-10-29 10:45 ` [PATCH v20 19/20] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-11-02 20:44   ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 20/20] mm/lru: revise the comments of lru_lock Alex Shi
2020-11-02 20:46   ` Johannes Weiner
2020-11-04 11:55 ` [PATCH v20 00/20] per memcg lru lock Alex Shi
2020-11-04 16:59   ` Johannes Weiner
2020-11-05  5:07     ` Alex Shi

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=1603968305-8026-1-git-send-email-alex.shi@linux.alibaba.com \
    --to=alex.shi@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=daniel.m.jordan@oracle.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=khlebnikov@yandex-team.ru \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@intel.com \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=richard.weiyang@gmail.com \
    --cc=rong.a.chen@intel.com \
    --cc=shakeelb@google.com \
    --cc=shy828301@gmail.com \
    --cc=tj@kernel.org \
    --cc=vdavydov.dev@gmail.com \
    --cc=willy@infradead.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).