From: Andrea Arcangeli <aarcange@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Minchan Kim <minchan.kim@gmail.com>,
Michel Lespinasse <walken@google.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Hugh Dickins <hughd@google.com>,
Johannes Weiner <jweiner@redhat.com>,
Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Shaohua Li <shaohua.li@intel.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: [PATCH] thp: tail page refcounting fix #5
Date: Fri, 2 Sep 2011 02:20:13 +0200 [thread overview]
Message-ID: <20110902002013.GJ10779@redhat.com> (raw)
In-Reply-To: <20110901234527.GD7761@one.firstfloor.org>
On Fri, Sep 02, 2011 at 01:45:27AM +0200, Andi Kleen wrote:
> On Thu, Sep 01, 2011 at 04:28:08PM -0700, Andrew Morton wrote:
> > On Thu, 1 Sep 2011 17:24:17 +0200
> > Andrea Arcangeli <aarcange@redhat.com> wrote:
> >
> > > Ideally direct-io should stop calling get_page() on pages
> > > returned by get_user_pages().
> >
> > Yeah. get_user_pages() is sufficient. Ideally we should be able to
> > undo the get_user_pages() get_page() from within the IO completion
> > interrupt and we're done.
> >
> > Cc Andi, who is our resident dio tweaker ;)
>
> Noted, I'll put it on my list.
Thanks Andi!
> Should not be too difficult from a quick look, just the convoluted
> nature of direct-io.c requires a lot of double checking.
I also had a look but it wasn't trivial, I'm not even sure why
direct-io.c has to be convoluted.
If we could optimize that, we would stay within get_page_foll() which
won't need to take the compound_lock even for tail
pages. (compound_lock can't be avoided for put_page on tail pages
because it runs long after we release any VM lock)
Calling get_page/put_pages more times than necessary is never ideal, I
imagine the biggest cost is the atomic_inc on the head page that
brings in the cacheline of the head page exclusive, the compound_lock
in the second get_page shouldn't have a measurable effect, so I think
from a practical prospective it's not more worthwhile to optimize
that now, than it already was before.
> Cc Andi, who is our resident dio tweaker ;)
Thanks :)
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-09-02 0:20 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-19 7:48 [PATCH 0/9] Use RCU to stabilize page counts Michel Lespinasse
2011-08-19 7:48 ` [PATCH 1/9] mm: rcu read lock for getting reference on pages in migration_entry_wait() Michel Lespinasse
2011-08-19 7:48 ` [PATCH 2/9] mm: avoid calling get_page_unless_zero() when charging cgroups Michel Lespinasse
2011-08-19 7:48 ` [PATCH 3/9] mm: rcu read lock when getting from tail to head page Michel Lespinasse
2011-08-19 7:48 ` [PATCH 4/9] mm: use get_page in deactivate_page() Michel Lespinasse
2011-08-19 7:48 ` [PATCH 5/9] kvm: use get_page instead of get_page_unless_zero Michel Lespinasse
2011-08-19 7:48 ` [PATCH 6/9] mm: assert that get_page_unless_zero() callers hold the rcu lock Michel Lespinasse
2011-08-19 23:28 ` Andi Kleen
2011-08-19 7:48 ` [PATCH 7/9] rcu: rcu_get_gp_cookie() / rcu_gp_cookie_elapsed() stand-ins Michel Lespinasse
2011-08-19 7:48 ` [PATCH 8/9] mm: add API for setting a grace period cookie on compound pages Michel Lespinasse
2011-08-19 7:48 ` [PATCH 9/9] mm: make sure tail page counts are stable before splitting THP pages Michel Lespinasse
2011-08-19 7:53 ` [PATCH 0/9] Use RCU to stabilize page counts Michel Lespinasse
2011-08-22 21:33 ` [PATCH] thp: tail page refcounting fix Andrea Arcangeli
2011-08-23 14:55 ` Andrea Arcangeli
2011-08-23 16:45 ` Minchan Kim
2011-08-23 16:54 ` Andrea Arcangeli
2011-08-23 19:52 ` Michel Lespinasse
2011-08-24 0:09 ` Andrea Arcangeli
2011-08-24 0:27 ` Andrea Arcangeli
2011-08-24 13:34 ` [PATCH] thp: tail page refcounting fix #2 Andrea Arcangeli
2011-08-26 6:24 ` Michel Lespinasse
2011-08-26 16:10 ` Andrea Arcangeli
2011-08-26 18:54 ` [PATCH] thp: tail page refcounting fix #3 Andrea Arcangeli
2011-08-27 9:41 ` Michel Lespinasse
2011-08-27 17:34 ` [PATCH] thp: tail page refcounting fix #4 Andrea Arcangeli
2011-08-29 4:20 ` Minchan Kim
2011-09-01 15:24 ` [PATCH] thp: tail page refcounting fix #5 Andrea Arcangeli
2011-09-01 22:27 ` Michel Lespinasse
2011-09-01 23:28 ` Andrew Morton
2011-09-01 23:45 ` Andi Kleen
2011-09-02 0:20 ` Andrea Arcangeli [this message]
2011-09-02 1:17 ` Andi Kleen
2011-09-02 0:03 ` Andrew Morton
2011-09-08 16:51 ` [PATCH] thp: tail page refcounting fix #6 Andrea Arcangeli
2011-09-23 15:57 ` Peter Zijlstra
2011-09-30 13:58 ` Andrea Arcangeli
2011-10-16 20:37 ` thp: gup_fast ppc tail refcounting [was Re: [PATCH] thp: tail page refcounting fix #6] Andrea Arcangeli
2011-10-16 20:37 ` [PATCH 1/4] powerpc: remove superfluous PageTail checks on the pte gup_fast Andrea Arcangeli
2011-10-16 20:37 ` [PATCH 2/4] powerpc: get_hugepte() don't put_page() the wrong page Andrea Arcangeli
2011-10-16 20:37 ` [PATCH 3/4] powerpc: gup_hugepte() avoid to free the head page too many times Andrea Arcangeli
2011-10-16 20:37 ` [PATCH 4/4] powerpc: gup_hugepte() support THP based tail recounting Andrea Arcangeli
2011-10-16 20:40 ` thp: gup_fast ppc tail refcounting [was Re: [PATCH] thp: tail page refcounting fix #6] Andrea Arcangeli
2011-10-16 20:40 ` [PATCH 1/4] powerpc: remove superfluous PageTail checks on the pte gup_fast Andrea Arcangeli
2011-10-16 20:40 ` [PATCH 2/4] powerpc: get_hugepte() don't put_page() the wrong page Andrea Arcangeli
2011-10-16 20:40 ` [PATCH 3/4] powerpc: gup_hugepte() avoid to free the head page too many times Andrea Arcangeli
2011-10-16 20:40 ` [PATCH 4/4] powerpc: gup_hugepte() support THP based tail recounting Andrea Arcangeli
2011-10-17 14:41 ` thp: gup_fast s390/sparc tail refcounting [was Re: [PATCH] thp: tail page refcounting fix #6] Andrea Arcangeli
2011-10-17 14:41 ` [PATCH 1/3] s390: gup_huge_pmd() support THP tail recounting Andrea Arcangeli
2011-10-17 14:41 ` [PATCH 2/3] sparc: gup_pte_range() support THP based " Andrea Arcangeli
2011-10-17 22:44 ` David Miller
2011-10-17 14:41 ` [PATCH 3/3] thp: share get_huge_page_tail() Andrea Arcangeli
2011-10-17 21:32 ` fix two more s390/sparc gup_fast bugs Andrea Arcangeli
2011-10-17 21:32 ` [PATCH 1/2] s390: gup_huge_pmd() return 0 if pte changes Andrea Arcangeli
2011-10-17 21:32 ` [PATCH 2/2] powerpc: " Andrea Arcangeli
2011-08-29 22:40 ` [PATCH] thp: tail page refcounting fix #4 Michel Lespinasse
2011-08-29 23:30 ` Andrea Arcangeli
2011-08-26 19:28 ` [PATCH] thp: tail page refcounting fix #2 Andrea Arcangeli
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=20110902002013.GJ10779@redhat.com \
--to=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=hughd@google.com \
--cc=jweiner@redhat.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=minchan.kim@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=shaohua.li@intel.com \
--cc=walken@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
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).