From: Minchan Kim <minchan@kernel.org>
To: David Hildenbrand <david@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
mhocko@suse.com, joaodias@google.com
Subject: Re: [PATCH] mm: be more verbose for alloc_contig_range faliures
Date: Wed, 17 Feb 2021 09:26:14 -0800 [thread overview]
Message-ID: <YC1RtmdhUR40gAzq@google.com> (raw)
In-Reply-To: <854d4ec8-1eb9-3595-b867-3e50f5a0e6a8@redhat.com>
On Wed, Feb 17, 2021 at 05:51:27PM +0100, David Hildenbrand wrote:
> On 17.02.21 17:36, Minchan Kim wrote:
> > alloc_contig_range is usually used on cma area or movable zone.
> > It's critical if the page migration fails on those areas so
> > dump more debugging message like memory_hotplug unless user
> > specifiy __GFP_NOWARN.
> >
> > Signed-off-by: Minchan Kim <minchan@kernel.org>
> > ---
> > mm/page_alloc.c | 16 +++++++++++++++-
> > 1 file changed, 15 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 0b55c9c95364..67f3ee3a1528 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -8486,6 +8486,15 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
> > NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
> > }
> > if (ret < 0) {
> > + if (!(cc->gfp_mask & __GFP_NOWARN)) {
> > + struct page *page;
> > +
> > + list_for_each_entry(page, &cc->migratepages, lru) {
> > + pr_warn("migrating pfn %lx failed ret:%d ",
> > + page_to_pfn(page), ret);
> > + dump_page(page, "migration failure");
> > + }
>
> This can create *a lot* of noise. For example, until huge pages are actually
> considered, we will choke on each end every huge page - and might do so over
> and over again.
I am not familiar with huge page status at this moment but why couldn't
they use __GFP_NOWARN if they are supposed to fail frequently?
>
> This might be helpful for debugging, but is unacceptable for production
> systems for now I think. Maybe for now, do it based on CONFIG_DEBUG_VM.
If it's due to huge page you mentioned above and caller passes
__GFP_NOWARN in that case, couldn't we enable always-on?
Actually, I am targeting cma allocation failure, which should
be rather rare compared to other call sites but critical to fail.
If it's concern to emit too many warning message, I will scope
down for site for only cma allocation.
>
> > + }
> > putback_movable_pages(&cc->migratepages);
> > return ret;
> > }
> > @@ -8728,6 +8737,8 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
> > pfn = ALIGN(zone->zone_start_pfn, nr_pages);
> > while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
> > if (pfn_range_valid_contig(zone, pfn, nr_pages)) {
> > + unsigned long gfp_flags;
> > +
> > /*
> > * We release the zone lock here because
> > * alloc_contig_range() will also lock the zone
> > @@ -8736,8 +8747,11 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
> > * and cause alloc_contig_range() to fail...
> > */
> > spin_unlock_irqrestore(&zone->lock, flags);
> > +
> > + if (zone_idx(zone) != ZONE_MOVABLE)
> > + gfp_flags = gfp_mask | __GFP_NOWARN;
>
> This feels wrong. It might be better to make that decision inside
> __alloc_contig_migrate_range() based on cc->zone.
CMA could be any normal zone and the suggestion will make it slient.
next prev parent reply other threads:[~2021-02-17 17:26 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-17 16:36 [PATCH] mm: be more verbose for alloc_contig_range faliures Minchan Kim
2021-02-17 16:51 ` David Hildenbrand
2021-02-17 17:26 ` Minchan Kim [this message]
2021-02-17 17:34 ` David Hildenbrand
2021-02-17 17:45 ` Minchan Kim
2021-02-18 8:56 ` Michal Hocko
2021-02-18 9:02 ` David Hildenbrand
2021-02-18 9:35 ` Michal Hocko
2021-02-18 9:43 ` David Hildenbrand
2021-02-18 9:59 ` Michal Hocko
2021-02-18 16:19 ` Minchan Kim
2021-02-18 16:26 ` David Hildenbrand
2021-02-18 16:47 ` Minchan Kim
2021-02-18 16:53 ` David Hildenbrand
2021-02-19 9:28 ` Michal Hocko
2021-02-19 9:30 ` David Hildenbrand
2021-02-19 10:02 ` Michal Hocko
2021-02-19 10:34 ` David Hildenbrand
[not found] ` <YD50pcPuwV456vwm@google.com>
2021-03-04 16:01 ` Minchan Kim
2021-03-04 16:10 ` David Hildenbrand
2021-03-04 16:23 ` Minchan Kim
2021-03-04 16:28 ` David Hildenbrand
2021-03-04 17:11 ` Minchan Kim
2021-03-04 17:23 ` David Hildenbrand
2021-03-04 18:11 ` Minchan Kim
2021-03-04 18:22 ` Minchan Kim
2021-03-08 12:49 ` Michal Hocko
2021-03-08 13:22 ` David Hildenbrand
2021-03-08 14:11 ` Michal Hocko
2021-03-08 14:13 ` David Hildenbrand
2021-03-08 15:42 ` Michal Hocko
2021-03-08 15:58 ` Minchan Kim
2021-03-08 16:21 ` Michal Hocko
2021-03-08 17:01 ` Minchan Kim
2021-03-08 20:27 ` Minchan Kim
2021-02-18 16:10 ` 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=YC1RtmdhUR40gAzq@google.com \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=joaodias@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.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).