From: Mel Gorman <mgorman@suse.de>
To: Mike Kravetz <mike.kravetz@oracle.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Hillf Danton <hdanton@sina.com>, Michal Hocko <mhocko@kernel.org>,
Vlastimil Babka <vbabka@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [RFC PATCH 3/3] hugetlbfs: don't retry when pool page allocations start to fail
Date: Thu, 25 Jul 2019 23:43:07 +0100 [thread overview]
Message-ID: <20190725224307.GE2708@suse.de> (raw)
In-Reply-To: <6a7f3705-9550-e22f-efa1-5e3616351df6@oracle.com>
On Thu, Jul 25, 2019 at 10:15:29AM -0700, Mike Kravetz wrote:
> On 7/25/19 1:13 AM, Mel Gorman wrote:
> > On Wed, Jul 24, 2019 at 10:50:14AM -0700, Mike Kravetz wrote:
> >> When allocating hugetlbfs pool pages via /proc/sys/vm/nr_hugepages,
> >> the pages will be interleaved between all nodes of the system. If
> >> nodes are not equal, it is quite possible for one node to fill up
> >> before the others. When this happens, the code still attempts to
> >> allocate pages from the full node. This results in calls to direct
> >> reclaim and compaction which slow things down considerably.
> >>
> >> When allocating pool pages, note the state of the previous allocation
> >> for each node. If previous allocation failed, do not use the
> >> aggressive retry algorithm on successive attempts. The allocation
> >> will still succeed if there is memory available, but it will not try
> >> as hard to free up memory.
> >>
> >> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
> >
> > set_max_huge_pages can fail the NODEMASK_ALLOC() alloc which you handle
> > *but* in the event of an allocation failure this bug can silently recur.
> > An informational message might be justified in that case in case the
> > stall should recur with no hint as to why.
>
> Right.
> Perhaps a NODEMASK_ALLOC() failure should just result in a quick exit/error.
> If we can't allocate a node mask, it is unlikely we will be able to allocate
> a/any huge pages. And, the system must be extremely low on memory and there
> are likely other bigger issues.
>
That might be better overall, you make a valid point that a failed
kmalloc is not a good sign for hugetlbfs allocations.
> There have been discussions elsewhere about discontinuing the use of
> NODEMASK_ALLOC() and just putting the mask on the stack. That may be
> acceptable here as well.
>
They can be big and while this particular path would be relatively safe,
I think the fact that there will not be much functional difference
between allocating on the stack and a failed kmalloc in terms of
hugetlbfs allocation success rates.
> > Technically passing NULL into
> > NODEMASK_FREE is also safe as kfree (if used for that kernel config) can
> > handle freeing of a NULL pointer. However, that is cosmetic more than
> > anything. Whether you decide to change either or not;
>
> Yes.
> I will clean up with an updated series after more feedback.
>
Thanks.
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2019-07-25 22:43 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-24 17:50 [RFC PATCH 0/3] fix hugetlb page allocation stalls Mike Kravetz
2019-07-24 17:50 ` [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection Mike Kravetz
2019-07-25 8:05 ` Mel Gorman
2019-07-26 8:12 ` Mel Gorman
2019-07-31 11:08 ` Vlastimil Babka
2019-07-31 12:25 ` Mel Gorman
2019-07-31 21:11 ` Mike Kravetz
2019-08-01 8:44 ` Vlastimil Babka
2019-07-24 17:50 ` [RFC PATCH 2/3] mm, compaction: use MIN_COMPACT_COSTLY_PRIORITY everywhere for costly orders Mike Kravetz
2019-07-25 8:06 ` Mel Gorman
2019-07-31 12:06 ` Vlastimil Babka
2019-07-31 20:30 ` Mike Kravetz
2019-08-01 13:01 ` Vlastimil Babka
2019-08-01 20:33 ` Mike Kravetz
2019-08-02 10:20 ` Vlastimil Babka
2019-08-02 12:05 ` Vlastimil Babka
2019-08-02 17:44 ` Mike Kravetz
2019-07-24 17:50 ` [RFC PATCH 3/3] hugetlbfs: don't retry when pool page allocations start to fail Mike Kravetz
2019-07-25 8:13 ` Mel Gorman
2019-07-25 17:15 ` Mike Kravetz
2019-07-25 22:43 ` Mel Gorman [this message]
2019-07-31 13:23 ` Vlastimil Babka
2019-07-31 21:13 ` Mike Kravetz
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=20190725224307.GE2708@suse.de \
--to=mgorman@suse.de \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=hdanton@sina.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=vbabka@suse.cz \
/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).