From: Vlastimil Babka <vbabka@suse.cz>
To: Mel Gorman <mgorman@techsingularity.net>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Shantanu Goel <sgoel01@yahoo.com>, Chris Mason <clm@fb.com>,
Johannes Weiner <hannes@cmpxchg.org>,
LKML <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>
Subject: Re: [PATCH 3/3] mm, vmscan: Prevent kswapd sleeping prematurely due to mismatched classzone_idx
Date: Wed, 1 Mar 2017 10:04:52 +0100 [thread overview]
Message-ID: <f84b532c-85f5-753e-a0aa-f5eb37995db2@suse.cz> (raw)
In-Reply-To: <20170223150108.sjw3mghjh3jvrbjn@techsingularity.net>
On 02/23/2017 04:01 PM, Mel Gorman wrote:
> On Mon, Feb 20, 2017 at 05:42:49PM +0100, Vlastimil Babka wrote:
>>> With this patch on top, all the latencies relative to the baseline are
>>> improved, particularly write latencies. The read latencies are still high
>>> for the number of threads but it's worth noting that this is mostly due
>>> to the IO scheduler and not directly related to reclaim. The vmstats are
>>> a bit of a mix but the relevant ones are as follows;
>>>
>>> 4.10.0-rc7 4.10.0-rc7 4.10.0-rc7
>>> mmots-20170209 clear-v1r25keepawake-v1r25
>>> Swap Ins 0 0 0
>>> Swap Outs 0 608 0
>>> Direct pages scanned 6910672 3132699 6357298
>>> Kswapd pages scanned 57036946 82488665 56986286
>>> Kswapd pages reclaimed 55993488 63474329 55939113
>>> Direct pages reclaimed 6905990 2964843 6352115
>>
>> These stats are confusing me. The earlier description suggests that this patch
>> should cause less direct reclaim and more kswapd reclaim, but compared to
>> "clear-v1r25" it does the opposite? Was clear-v1r25 overreclaiming then? (when
>> considering direct + kswapd combined)
>>
>
> The description is referring to the impact relative to baseline. It is
> true that relative to patch that direct reclaim is higher but there are
> a number of anomalies.
>
> Note that kswapd is scanning very aggressively in "clear-v1" and overall
> efficiency is down to 76%. It's also not clear in the stats but in
> "clear-v1", pgskip_* is active as the wrong zone is being reclaimed for
> due to the patch "mm, vmscan: fix zone balance check in
> prepare_kswapd_sleep". It's also doing a lot of writing of file-backed
> pages from reclaim context and some swapping due to the aggressiveness
> of the scan.
>
> While direct reclaim activity might be lower, it's due to kswapd scanning
> aggressively and trying to reclaim the world which is not the right thing
> to do. With the patches applied, there is still direct reclaim but the fast
> bulk of them are when the workload changes phase from "creating work files"
> to starting multiple threads that allocate a lot of anonymous memory with
> a sudden spike in memory pressure that kswapd does not keep ahead of with
> multiple allocating threads.
Thanks for the explanation.
>
>>> @@ -3328,6 +3330,22 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
>>> return sc.order;
>>> }
>>>
>>> +/*
>>> + * pgdat->kswapd_classzone_idx is the highest zone index that a recent
>>> + * allocation request woke kswapd for. When kswapd has not woken recently,
>>> + * the value is MAX_NR_ZONES which is not a valid index. This compares a
>>> + * given classzone and returns it or the highest classzone index kswapd
>>> + * was recently woke for.
>>> + */
>>> +static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
>>> + enum zone_type classzone_idx)
>>> +{
>>> + if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
>>> + return classzone_idx;
>>> +
>>> + return max(pgdat->kswapd_classzone_idx, classzone_idx);
>>
>> A bit paranoid comment: this should probably read pgdat->kswapd_classzone_idx to
>> a local variable with READ_ONCE(), otherwise something can set it to
>> MAX_NR_ZONES between the check and max(), and compiler can decide to reread.
>> Probably not an issue with current callers, but I'd rather future-proof it.
>>
>
> I'm a little wary of adding READ_ONCE unless there is a definite
> problem. Even if it was an issue, I think it would be better to protect
> thse kswapd_classzone_idx and kswapd_order with a spinlock that is taken
> if an update is required or a read to fully guarantee the ordering.
>
> The consequences as they are is that kswapd may miss reclaiming at a
> higher order or classzone than it should have although it is very
> unlikely and the update and read are made with a workqueue wake and
> scheduler wakeup which should be sufficient in terms of barriers.
OK then.
Acked-by: Vlastimil Babka <vbabka@suse.cz>
next prev parent reply other threads:[~2017-03-01 9:25 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-15 9:22 [PATCH 0/3] Reduce amount of time kswapd sleeps prematurely Mel Gorman
2017-02-15 9:22 ` [PATCH 1/3] mm, vmscan: fix zone balance check in prepare_kswapd_sleep Mel Gorman
2017-02-16 2:50 ` Hillf Danton
2017-02-22 7:00 ` Minchan Kim
2017-02-23 15:05 ` Mel Gorman
2017-02-24 1:17 ` Minchan Kim
2017-02-24 9:11 ` Mel Gorman
2017-02-27 6:16 ` Minchan Kim
2017-02-15 9:22 ` [PATCH 2/3] mm, vmscan: Only clear pgdat congested/dirty/writeback state when balanced Mel Gorman
2017-02-15 9:22 ` [PATCH 3/3] mm, vmscan: Prevent kswapd sleeping prematurely due to mismatched classzone_idx Mel Gorman
2017-02-16 6:23 ` Hillf Danton
2017-02-16 8:10 ` Mel Gorman
2017-02-16 8:21 ` Hillf Danton
2017-02-16 9:32 ` Mel Gorman
2017-02-20 16:34 ` Vlastimil Babka
2017-02-21 4:10 ` Hillf Danton
2017-02-20 16:42 ` Vlastimil Babka
2017-02-23 15:01 ` Mel Gorman
2017-03-01 9:04 ` Vlastimil Babka [this message]
2017-02-15 20:30 ` [PATCH 0/3] Reduce amount of time kswapd sleeps prematurely Andrew Morton
2017-02-15 21:29 ` Mel Gorman
2017-02-15 21:56 ` Andrew Morton
2017-02-15 22:15 ` Mel Gorman
2017-02-15 22:00 ` Vlastimil Babka
2017-03-09 7:56 [PATCH 0/3] Reduce amount of time kswapd sleeps prematurely v2 Mel Gorman
2017-03-09 7:56 ` [PATCH 3/3] mm, vmscan: Prevent kswapd sleeping prematurely due to mismatched classzone_idx Mel Gorman
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=f84b532c-85f5-753e-a0aa-f5eb37995db2@suse.cz \
--to=vbabka@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=clm@fb.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=sgoel01@yahoo.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).