From: Mike Kravetz <mike.kravetz@oracle.com>
To: Vlastimil Babka <vbabka@suse.cz>, Hillf Danton <hdanton@sina.com>,
Mel Gorman <mgorman@suse.de>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Michal Hocko <mhocko@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection
Date: Wed, 31 Jul 2019 14:11:00 -0700 [thread overview]
Message-ID: <f6e25e52-bb02-6d79-b9fd-3acc8358ec45@oracle.com> (raw)
In-Reply-To: <295a37b1-8257-9b4a-b586-9a4990cc9d35@suse.cz>
On 7/31/19 4:08 AM, Vlastimil Babka wrote:
>
> I agree this is an improvement overall, but perhaps the patch does too
> many things at once. The reshuffle is one thing and makes sense. The
> change of the last return condition could perhaps be separate. Also
> AFAICS the ultimate result is that when nr_reclaimed == 0, the function
> will now always return false. Which makes the initial test for
> __GFP_RETRY_MAYFAIL and the comments there misleading. There will no
> longer be a full LRU scan guaranteed - as long as the scanned LRU chunk
> yields no reclaimed page, we abort.
Can someone help me understand why nr_scanned == 0 guarantees a full
LRU scan? FWICS, nr_scanned used in this context is only incremented
in shrink_page_list and potentially shrink_zones. In the stall case I
am looking at, there are MANY cases in which nr_scanned is only a few
pages and none of those are reclaimed.
Can we not get nr_scanned == 0 on an arbitrary chunk of the LRU?
I must be missing something, because I do not see how nr_scanned == 0
guarantees a full scan.
--
Mike Kravetz
WARNING: multiple messages have this Message-ID
From: Hillf Danton <hdanton@sina.com>
To: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>, Mel Gorman <mgorman@suse.de>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Michal Hocko <mhocko@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection
Date: Thu, 1 Aug 2019 12:22:40 +0800 [thread overview]
Message-ID: <f6e25e52-bb02-6d79-b9fd-3acc8358ec45@oracle.com> (raw)
Message-ID: <20190801042240.J5_QWR8RtBnRI3AikCWC67iK8-3xY6p246pjxX4Nqbg@z> (raw)
In-Reply-To: <295a37b1-8257-9b4a-b586-9a4990cc9d35@suse.cz>
On Wed, 31 Jul 2019 14:11:02 -0700 Mike Kravetz wrote:
>
> On 7/31/19 4:08 AM, Vlastimil Babka wrote:
> >
> > I agree this is an improvement overall, but perhaps the patch does too
> > many things at once. The reshuffle is one thing and makes sense. The
> > change of the last return condition could perhaps be separate. Also
> > AFAICS the ultimate result is that when nr_reclaimed == 0, the function
> > will now always return false. Which makes the initial test for
> > __GFP_RETRY_MAYFAIL and the comments there misleading. There will no
> > longer be a full LRU scan guaranteed - as long as the scanned LRU chunk
> > yields no reclaimed page, we abort.
>
> Can someone help me understand why nr_scanned == 0 guarantees a full
> LRU scan?
AFAIC no pages reclaimed without pages scanned(no scanning no reclaiming).
Literally a reclaimer's KPI is usually gauged by its effeicency of
reclaiming pages, irrespective of factors like the proportion of dirty
pages, costly order, the online of a swap disk and lru size.
At the moment nr_scanned == 0 raises a red light and the reclaimer has
to take right actions accordingly. Currently there is no ruleout of a
full lru scan.
Feel free to correct me if anything missing.
Hillf
next prev parent reply other threads:[~2019-07-31 21:11 UTC|newest]
Thread overview: 26+ 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 7:40 ` Hillf Danton
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 [this message]
2019-08-01 4:22 ` Hillf Danton
2019-08-01 8:44 ` Vlastimil Babka
2019-08-01 3:16 ` Hillf Danton
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
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=f6e25e52-bb02-6d79-b9fd-3acc8358ec45@oracle.com \
--to=mike.kravetz@oracle.com \
--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=mgorman@suse.de \
--cc=mhocko@kernel.org \
--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