From: Minchan Kim <minchan@kernel.org>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
jlayton@poochiereds.net, bfields@fieldses.org,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
koct9i@gmail.com, aquini@redhat.com,
virtualization@lists.linux-foundation.org,
Mel Gorman <mgorman@suse.de>, Hugh Dickins <hughd@google.com>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
rknize@motorola.com, Rik van Riel <riel@redhat.com>,
Gioh Kim <gurugio@hanmail.net>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Subject: Re: [PATCH v1 01/19] mm: use put_page to free page instead of putback_lru_page
Date: Tue, 15 Mar 2016 10:16:56 +0900 [thread overview]
Message-ID: <20160315011656.GD19514@bbox> (raw)
In-Reply-To: <56E67AE1.60700@suse.cz>
On Mon, Mar 14, 2016 at 09:48:33AM +0100, Vlastimil Babka wrote:
> On 03/11/2016 08:30 AM, Minchan Kim wrote:
> >Procedure of page migration is as follows:
> >
> >First of all, it should isolate a page from LRU and try to
> >migrate the page. If it is successful, it releases the page
> >for freeing. Otherwise, it should put the page back to LRU
> >list.
> >
> >For LRU pages, we have used putback_lru_page for both freeing
> >and putback to LRU list. It's okay because put_page is aware of
> >LRU list so if it releases last refcount of the page, it removes
> >the page from LRU list. However, It makes unnecessary operations
> >(e.g., lru_cache_add, pagevec and flags operations.
>
> Yeah, and compaction (perhaps also other migration users) has to
> drain the lru pvec... Getting rid of this stuff is worth even by
> itself.
Good note. Although we cannot remove lru pvec draining completely,
at least, this patch removes a case which should drain pvec for
returning freed page to buddy.
Thanks for the notice.
>
> >It would be
> >not significant but no worth to do) and harder to support new
> >non-lru page migration because put_page isn't aware of non-lru
> >page's data structure.
> >
> >To solve the problem, we can add new hook in put_page with
> >PageMovable flags check but it can increase overhead in
> >hot path and needs new locking scheme to stabilize the flag check
> >with put_page.
> >
> >So, this patch cleans it up to divide two semantic(ie, put and putback).
> >If migration is successful, use put_page instead of putback_lru_page and
> >use putback_lru_page only on failure. That makes code more readable
> >and doesn't add overhead in put_page.
>
> I had an idea of checking for count==1 in putback_lru_page() which
> would take the put_page() shortcut from there. But maybe it can't be
> done nicely without races.
I thought about it and we might do it via page_freeze_refs but
what I want at this moment is to separte two semantic put and putback.
;-)
>
> >Cc: Vlastimil Babka <vbabka@suse.cz>
> >Cc: Mel Gorman <mgorman@suse.de>
> >Cc: Hugh Dickins <hughd@google.com>
> >Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
> >Signed-off-by: Minchan Kim <minchan@kernel.org>
>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
>
> Note in -next/after 4.6-rc1 this will need some rebasing though.
Thanks for the review!
next prev parent reply other threads:[~2016-03-15 1:16 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-11 7:30 [PATCH v1 00/19] Support non-lru page migration Minchan Kim
2016-03-11 7:30 ` [PATCH v1 01/19] mm: use put_page to free page instead of putback_lru_page Minchan Kim
2016-03-14 8:48 ` Vlastimil Babka
2016-03-15 1:16 ` Minchan Kim [this message]
2016-03-15 19:06 ` Vlastimil Babka
2016-03-11 7:30 ` [PATCH v1 02/19] mm/compaction: support non-lru movable page migration Minchan Kim
2016-03-11 8:11 ` kbuild test robot
2016-03-11 8:35 ` Minchan Kim
2016-03-11 7:30 ` [PATCH v1 03/19] fs/anon_inodes: new interface to create new inode Minchan Kim
2016-03-11 8:05 ` Al Viro
2016-03-11 14:24 ` Gioh Kim
2016-03-11 7:30 ` [PATCH v1 04/19] mm/balloon: use general movable page feature into balloon Minchan Kim
2016-03-11 7:30 ` [PATCH v1 05/19] zsmalloc: use first_page rather than page Minchan Kim
2016-03-15 6:19 ` Sergey Senozhatsky
2016-03-11 7:30 ` [PATCH v1 06/19] zsmalloc: clean up many BUG_ON Minchan Kim
2016-03-15 6:19 ` Sergey Senozhatsky
2016-03-11 7:30 ` [PATCH v1 07/19] zsmalloc: reordering function parameter Minchan Kim
2016-03-15 6:20 ` Sergey Senozhatsky
2016-03-11 7:30 ` [PATCH v1 08/19] zsmalloc: remove unused pool param in obj_free Minchan Kim
2016-03-15 6:21 ` Sergey Senozhatsky
2016-03-11 7:30 ` [PATCH v1 09/19] zsmalloc: keep max_object in size_class Minchan Kim
2016-03-12 1:44 ` xuyiping
2016-03-14 4:55 ` Minchan Kim
2016-03-15 6:28 ` Sergey Senozhatsky
2016-03-15 6:41 ` Minchan Kim
2016-03-11 7:30 ` [PATCH v1 10/19] zsmalloc: squeeze inuse into page->mapping Minchan Kim
2016-03-11 7:30 ` [PATCH v1 11/19] zsmalloc: squeeze freelist " Minchan Kim
2016-03-15 6:40 ` Sergey Senozhatsky
2016-03-15 6:51 ` Minchan Kim
2016-03-17 12:09 ` YiPing Xu
2016-03-17 22:17 ` Minchan Kim
2016-03-11 7:30 ` [PATCH v1 12/19] zsmalloc: move struct zs_meta from mapping to freelist Minchan Kim
2016-03-11 7:30 ` [PATCH v1 13/19] zsmalloc: factor page chain functionality out Minchan Kim
2016-03-12 3:09 ` xuyiping
2016-03-14 4:58 ` Minchan Kim
2016-03-11 7:30 ` [PATCH v1 14/19] zsmalloc: separate free_zspage from putback_zspage Minchan Kim
2016-03-11 7:30 ` [PATCH v1 15/19] zsmalloc: zs_compact refactoring Minchan Kim
2016-03-11 7:30 ` [PATCH v1 16/19] zsmalloc: migrate head page of zspage Minchan Kim
2016-03-11 7:30 ` [PATCH v1 17/19] zsmalloc: use single linked list for page chain Minchan Kim
2016-03-11 7:30 ` [PATCH v1 18/19] zsmalloc: migrate tail pages in zspage Minchan Kim
2016-03-11 7:30 ` [PATCH v1 19/19] zram: use __GFP_MOVABLE for memory allocation Minchan Kim
2016-03-15 6:56 ` Sergey Senozhatsky
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=20160315011656.GD19514@bbox \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=aquini@redhat.com \
--cc=bfields@fieldses.org \
--cc=gurugio@hanmail.net \
--cc=hughd@google.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=jlayton@poochiereds.net \
--cc=koct9i@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=n-horiguchi@ah.jp.nec.com \
--cc=riel@redhat.com \
--cc=rknize@motorola.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=vbabka@suse.cz \
--cc=virtualization@lists.linux-foundation.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).