LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Michal Hocko <mhocko@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-api@vger.kernel.org, Johannes Weiner <hannes@cmpxchg.org>,
	Tim Murray <timmurray@google.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Daniel Colascione <dancol@google.com>,
	Shakeel Butt <shakeelb@google.com>,
	Sonny Rao <sonnyrao@google.com>,
	Brian Geffon <bgeffon@google.com>,
	jannh@google.com, oleg@redhat.com, christian@brauner.io,
	oleksandr@redhat.com, hdanton@sina.com
Subject: Re: [RFCv2 1/6] mm: introduce MADV_COLD
Date: Tue, 4 Jun 2019 13:26:51 +0900
Message-ID: <20190604042651.GC43390@google.com> (raw)
In-Reply-To: <20190603071607.GB4531@dhcp22.suse.cz>

On Mon, Jun 03, 2019 at 09:16:07AM +0200, Michal Hocko wrote:
> On Fri 31-05-19 23:34:07, Minchan Kim wrote:
> > On Fri, May 31, 2019 at 04:03:32PM +0200, Michal Hocko wrote:
> > > On Fri 31-05-19 22:39:04, Minchan Kim wrote:
> > > > On Fri, May 31, 2019 at 10:47:52AM +0200, Michal Hocko wrote:
> > > > > On Fri 31-05-19 15:43:08, Minchan Kim wrote:
> > > > > > When a process expects no accesses to a certain memory range, it could
> > > > > > give a hint to kernel that the pages can be reclaimed when memory pressure
> > > > > > happens but data should be preserved for future use.  This could reduce
> > > > > > workingset eviction so it ends up increasing performance.
> > > > > > 
> > > > > > This patch introduces the new MADV_COLD hint to madvise(2) syscall.
> > > > > > MADV_COLD can be used by a process to mark a memory range as not expected
> > > > > > to be used in the near future. The hint can help kernel in deciding which
> > > > > > pages to evict early during memory pressure.
> > > > > > 
> > > > > > Internally, it works via deactivating pages from active list to inactive's
> > > > > > head if the page is private because inactive list could be full of
> > > > > > used-once pages which are first candidate for the reclaiming and that's a
> > > > > > reason why MADV_FREE move pages to head of inactive LRU list. Therefore,
> > > > > > if the memory pressure happens, they will be reclaimed earlier than other
> > > > > > active pages unless there is no access until the time.
> > > > > 
> > > > > [I am intentionally not looking at the implementation because below
> > > > > points should be clear from the changelog - sorry about nagging ;)]
> > > > > 
> > > > > What kind of pages can be deactivated? Anonymous/File backed.
> > > > > Private/shared? If shared, are there any restrictions?
> > > > 
> > > > Both file and private pages could be deactived from each active LRU
> > > > to each inactive LRU if the page has one map_count. In other words,
> > > > 
> > > >     if (page_mapcount(page) <= 1)
> > > >         deactivate_page(page);
> > > 
> > > Why do we restrict to pages that are single mapped?
> > 
> > Because page table in one of process shared the page would have access bit
> > so finally we couldn't reclaim the page. The more process it is shared,
> > the more fail to reclaim.
> 
> So what? In other words why should it be restricted solely based on the
> map count. I can see a reason to restrict based on the access
> permissions because we do not want to simplify all sorts of side channel
> attacks but memory reclaim is capable of reclaiming shared pages and so
> far I haven't heard any sound argument why madvise should skip those.
> Again if there are any reasons, then document them in the changelog.

I will go with removing the part so that defer to decision to the VM reclaim
based on the review.

>  
> [...]
> 
> > > Please document this, if this is really a desirable semantic because
> > > then you have the same set of problems as we've had with the early
> > > MADV_FREE implementation mentioned above.
> > 
> > IIRC, the problem of MADV_FREE was that we couldn't discard freeable
> > pages because VM never scan anonymous LRU with swapless system.
> > However, it's not the our case because we should reclaim them, not
> > discarding.
> 
> Right. But there is still the page cache reclaim. Is it expected that
> an explicitly cold memory doesn't get reclaimed because we have a
> sufficient amount of page cache (a very common case) and we never age
> anonymous memory because of that?

If there are lots of used-once pages in file-LRU, I think there is no
need to reclaim anonymous pages because it needs bigger overhead due to
IO. It has been true for a long time in current VM policy.

Reclaim preference model based on hints is as following based on cost:

MADV_DONTNEED >> MADV_PAGEOUT > used-once pages > MADV_FREE >= MADV_COLD

It is desirable for the new hints to be placed in the reclaiming preference
order such that a) they don't overlap functionally with existing hints and
b) we have a balanced ordering of disruptive and non-disruptive hints.

  parent reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-31  6:43 [RFCv2 0/6] introduce memory hinting API for external process Minchan Kim
2019-05-31  6:43 ` [RFCv2 1/6] mm: introduce MADV_COLD Minchan Kim
2019-05-31  8:47   ` Michal Hocko
2019-05-31 13:39     ` Minchan Kim
2019-05-31 14:03       ` Michal Hocko
2019-05-31 14:34         ` Minchan Kim
2019-06-03  7:16           ` Michal Hocko
2019-06-03 15:43             ` Daniel Colascione
2019-06-03 17:27             ` Johannes Weiner
2019-06-03 20:32               ` Michal Hocko
2019-06-03 21:50                 ` Johannes Weiner
2019-06-03 23:02                   ` Minchan Kim
2019-06-04  6:56                     ` Michal Hocko
2019-06-04 12:06                     ` Johannes Weiner
2019-06-04  6:55                   ` Michal Hocko
2019-06-04  4:26             ` Minchan Kim [this message]
2019-06-04  7:02               ` Michal Hocko
2019-05-31  6:43 ` [RFCv2 2/6] mm: change PAGEREF_RECLAIM_CLEAN with PAGE_REFRECLAIM Minchan Kim
2019-05-31  6:43 ` [RFCv2 3/6] mm: introduce MADV_PAGEOUT Minchan Kim
2019-05-31  8:50   ` Michal Hocko
2019-05-31 13:44     ` Minchan Kim
2019-05-31 16:59   ` Johannes Weiner
2019-05-31 23:14     ` Minchan Kim
2019-05-31  6:43 ` [RFCv2 4/6] mm: factor out madvise's core functionality Minchan Kim
2019-05-31  7:04   ` Oleksandr Natalenko
2019-05-31 13:12     ` Minchan Kim
2019-05-31 14:35       ` Oleksandr Natalenko
2019-05-31 23:29         ` Minchan Kim
2019-06-05 13:27           ` Oleksandr Natalenko
2019-06-10 10:12             ` Minchan Kim
2019-05-31  6:43 ` [RFCv2 5/6] mm: introduce external memory hinting API Minchan Kim
2019-05-31  8:37   ` Michal Hocko
2019-05-31 13:19     ` Minchan Kim
2019-05-31 14:00       ` Michal Hocko
2019-05-31 14:11         ` Minchan Kim
2019-05-31 17:35   ` Daniel Colascione
2019-05-31  6:43 ` [RFCv2 6/6] mm: extend process_madvise syscall to support vector arrary Minchan Kim
2019-05-31 10:06   ` Yann Droneaud
2019-05-31 23:18     ` Minchan Kim

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=20190604042651.GC43390@google.com \
    --to=minchan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=bgeffon@google.com \
    --cc=christian@brauner.io \
    --cc=dancol@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=jannh@google.com \
    --cc=joel@joelfernandes.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=oleg@redhat.com \
    --cc=oleksandr@redhat.com \
    --cc=shakeelb@google.com \
    --cc=sonnyrao@google.com \
    --cc=surenb@google.com \
    --cc=timmurray@google.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git