From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mel@csn.ul.ie>, Wu Fengguang <fengguang.wu@intel.com>,
"Jun'ichi Nomura" <j-nomura@ce.jp.nec.com>,
linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 6/7] hugetlb: hugepage migration core
Date: Thu, 8 Jul 2010 14:44:26 +0900 [thread overview]
Message-ID: <20100708054426.GA19906@spritzera.linux.bs1.fc.nec.co.jp> (raw)
In-Reply-To: <20100707092719.GA3900@basil.fritz.box>
On Wed, Jul 07, 2010 at 11:27:19AM +0200, Andi Kleen wrote:
> > I see. I understood we should work on locking problem in now.
> > I digged and learned hugepage IO can happen in direct IO from/to
> > hugepage or coredump of hugepage user.
> >
> > We can resolve race between memory failure and IO by checking
> > page lock and writeback flag, right?
>
> Yes, but we have to make sure it's in the same page.
>
> As I understand the IO locking does not use the head page, that
> means migration may need to lock all the sub pages.
>
> Or fix IO locking to use head pages?
> >
> > BTW I surveyed direct IO code, but page lock seems not to be taken.
> > Am I missing something?
>
> That's expected I believe because applications are supposed to coordinate
> for direct IO (but then direct IO also drops page cache).
>
> But page lock is used to coordinate in the page cache for buffered IO.
This page cache is located on non-hugepage, isn't it?
If so, buffered IO is handled in the same manner as done for non-hugepage.
I think "hugepage under IO" is realized only in direct IO for now.
Direct IO is issued in page unit even if the target page is in hugepage,
so locking each subpages separately looks natural for me than auditing
head page.
next prev parent reply other threads:[~2010-07-08 5:46 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-02 5:47 [PATCH 0/7] hugepage migration Naoya Horiguchi
2010-07-02 5:47 ` [PATCH 1/7] hugetlb: add missing unlock in avoidcopy path in hugetlb_cow() Naoya Horiguchi
2010-07-02 8:31 ` Andi Kleen
2010-07-05 8:44 ` Naoya Horiguchi
2010-07-07 22:17 ` Andi Kleen
2010-07-02 5:47 ` [PATCH 2/7] hugetlb, HWPOISON: move PG_HWPoison bit check Naoya Horiguchi
2010-07-02 5:47 ` [PATCH 3/7] hugetlb: add allocate function for hugepage migration Naoya Horiguchi
2010-07-02 9:08 ` Andi Kleen
2010-07-05 8:46 ` Naoya Horiguchi
2010-07-05 9:28 ` Andi Kleen
2010-07-02 5:47 ` [PATCH 4/7] hugetlb: add hugepage check in mem_cgroup_{register,end}_migration() Naoya Horiguchi
2010-07-02 9:11 ` Andi Kleen
2010-07-02 5:47 ` [PATCH 5/7] hugetlb: pin oldpage in page migration Naoya Horiguchi
2010-07-05 9:45 ` Andi Kleen
2010-07-06 15:54 ` Christoph Lameter
2010-07-07 6:40 ` Naoya Horiguchi
2010-07-02 5:47 ` [PATCH 6/7] hugetlb: hugepage migration core Naoya Horiguchi
2010-07-05 9:59 ` Andi Kleen
2010-07-06 3:33 ` Naoya Horiguchi
2010-07-06 7:13 ` Andi Kleen
2010-07-07 6:05 ` Naoya Horiguchi
2010-07-07 9:27 ` Andi Kleen
2010-07-08 5:44 ` Naoya Horiguchi [this message]
2010-07-08 6:49 ` Andi Kleen
2010-07-06 16:02 ` Christoph Lameter
2010-07-07 6:44 ` Naoya Horiguchi
2010-07-06 16:00 ` Christoph Lameter
2010-07-07 6:45 ` Naoya Horiguchi
2010-07-02 5:47 ` [PATCH 7/7] hugetlb, HWPOISON: soft offlining for hugepage Naoya Horiguchi
2010-07-05 10:28 ` Andi Kleen
2010-07-02 8:30 ` [PATCH 0/7] hugepage migration Andi Kleen
2010-07-05 8:44 ` Naoya Horiguchi
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=20100708054426.GA19906@spritzera.linux.bs1.fc.nec.co.jp \
--to=n-horiguchi@ah.jp.nec.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=fengguang.wu@intel.com \
--cc=j-nomura@ce.jp.nec.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
/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).