From: Minchan Kim <minchan@kernel.org>
To: Xishi Qiu <qiuxishi@huawei.com>
Cc: Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
riel@redhat.com, aquini@redhat.com, linux-mm@kvack.org,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] mm: skip the page buddy block instead of one page
Date: Thu, 15 Aug 2013 13:24:43 +0900 [thread overview]
Message-ID: <20130815042434.GA3139@gmail.com> (raw)
In-Reply-To: <20130815041736.GA2592@gmail.com>
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
> Hello,
>
> On Thu, Aug 15, 2013 at 11:46:07AM +0800, Xishi Qiu wrote:
> > On 2013/8/15 10:44, Minchan Kim wrote:
> >
> > > Hi Xishi,
> > >
> > > On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
> > >> On 2013/8/15 2:00, Mel Gorman wrote:
> > >>
> > >>>>> Even if the page is still page buddy, there is no guarantee that it's
> > >>>>> the same page order as the first read. It could have be currently
> > >>>>> merging with adjacent buddies for example. There is also a really
> > >>>>> small race that a page was freed, allocated with some number stuffed
> > >>>>> into page->private and freed again before the second PageBuddy check.
> > >>>>> It's a bit of a hand grenade. How much of a performance benefit is there
> > >>>>
> > >>>> 1. Just worst case is skipping pageblock_nr_pages
> > >>>
> > >>> No, the worst case is that page_order returns a number that is
> > >>> completely garbage and low_pfn goes off the end of the zone
> > >>>
> > >>>> 2. Race is really small
> > >>>> 3. Higher order page allocation customer always have graceful fallback.
> > >>>>
> > >>
> > >> Hi Minchan,
> > >> I think in this case, we may get the wrong value from page_order(page).
> > >>
> > >> 1. page is in page buddy
> > >>
> > >>> if (PageBuddy(page)) {
> > >>
> > >> 2. someone allocated the page, and set page->private to another value
> > >>
> > >>> int nr_pages = (1 << page_order(page)) - 1;
> > >>
> > >> 3. someone freed the page
> > >>
> > >>> if (PageBuddy(page)) {
> > >>
> > >> 4. we will skip wrong pages
> > >
> > > So, what's the result by that?
> > > As I said, it's just skipping (pageblock_nr_pages -1) at worst case
> >
> > Hi Minchan,
> > I mean if the private is set to a large number, it will skip 2^private
> > pages, not (pageblock_nr_pages -1). I find somewhere will use page->private,
> > such as fs. Here is the comment about parivate.
> > /* Mapping-private opaque data:
> > * usually used for buffer_heads
> > * if PagePrivate set; used for
> > * swp_entry_t if PageSwapCache;
> > * indicates order in the buddy
> > * system if PG_buddy is set.
> > */
>
> Please read full thread in detail.
>
> Mel suggested following as
>
> if (PageBuddy(page)) {
> int nr_pages = (1 << page_order(page)) - 1;
> if (PageBuddy(page)) {
> nr_pages = min(nr_pages, MAX_ORDER_NR_PAGES - 1);
> low_pfn += nr_pages;
> continue;
> }
> }
>
> min(nr_pages, xxx) removes your concern but I think Mel's version
> isn't right. It should be aligned with pageblock boundary so I
> suggested following.
>
> if (PageBuddy(page)) {
> #ifdef CONFIG_MEMORY_ISOLATION
> unsigned long order = page_order(page);
> if (PageBuddy(page)) {
> low_pfn += (1 << order) - 1;
> low_pfn = min(low_pfn, end_pfn);
> }
> #endif
> continue;
> }
>
> so worst case is (pageblock_nr_pages - 1).
> but we don't need to add CONFIG_MEMORY_ISOLATION so my suggestion
> is following as.
>
> if (PageBuddy(page)) {
> unsigned long order = page_order(page);
> if (PageBuddy(page)) {
> low_pfn += (1 << order) - 1;
> low_pfn = min(low_pfn, end_pfn);
Maybe it should be low_pfn = min(low_pfn, end_pfn - 1).
> }
> continue;
> }
>
>
--
Kind regards,
Minchan Kim
next prev parent reply other threads:[~2013-08-15 4:24 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-14 4:45 [PATCH] mm: skip the page buddy block instead of one page Xishi Qiu
2013-08-14 7:07 ` Minchan Kim
2013-08-14 8:57 ` Mel Gorman
2013-08-14 9:14 ` Xishi Qiu
2013-08-14 15:52 ` Minchan Kim
2013-08-14 16:16 ` Mel Gorman
2013-08-14 16:39 ` Minchan Kim
2013-08-14 18:00 ` Mel Gorman
2013-08-14 19:11 ` Minchan Kim
2013-08-15 2:32 ` Xishi Qiu
2013-08-15 2:44 ` Minchan Kim
2013-08-15 3:46 ` Xishi Qiu
2013-08-15 4:17 ` Minchan Kim
2013-08-15 4:24 ` Minchan Kim [this message]
2013-08-15 7:45 ` Xishi Qiu
[not found] ` <20130815095102.GA4449@hacker.(null)>
2013-08-15 11:15 ` Xishi Qiu
2013-08-15 11:17 ` Xishi Qiu
2013-08-15 6:38 ` Xishi Qiu
2013-08-15 11:30 ` Mel Gorman
2013-08-15 13:19 ` Minchan Kim
2013-08-15 13:42 ` Mel Gorman
2013-08-15 14:16 ` Minchan Kim
2013-08-14 20:26 ` Andrew Morton
2013-08-14 22:22 ` Mel Gorman
2014-01-17 14:32 ` [PATCH] mm: Improve documentation of page_order Mel Gorman
2014-01-17 18:40 ` Rafael Aquini
2014-01-17 18:53 ` Laura Abbott
2014-01-17 19:59 ` Mel Gorman
2014-01-21 11:05 ` [PATCH] mm: Improve documentation of page_order v2 Mel Gorman
2014-01-20 6:12 ` [PATCH] mm: Improve documentation of page_order 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=20130815042434.GA3139@gmail.com \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=aquini@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=qiuxishi@huawei.com \
--cc=riel@redhat.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).