linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Mel Gorman <mgorman@techsingularity.net>
Cc: Linux-MM <linux-mm@kvack.org>, Rik van Riel <riel@surriel.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Li Zefan <lizefan@huawei.com>,
	cgroups@vger.kernel.org
Subject: Re: [PATCH 02/27] mm, vmscan: Check if cpusets are enabled during direct reclaim
Date: Wed, 9 Mar 2016 13:30:17 +0100	[thread overview]
Message-ID: <56E01759.5090203@suse.cz> (raw)
In-Reply-To: <20160309115909.GA31585@techsingularity.net>

On 03/09/2016 12:59 PM, Mel Gorman wrote:
> On Thu, Mar 03, 2016 at 12:31:40PM +0100, Vlastimil Babka wrote:
>> On 02/23/2016 04:04 PM, Mel Gorman wrote:
>>> Direct reclaim obeys cpusets but misses the cpusets_enabled() check.
>>> The overhead is unlikely to be measurable in the direct reclaim
>>> path which is expensive but there is no harm is doing it.
>>>
>>> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
>>> ---
>>>  mm/vmscan.c | 2 +-
>>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>> index 86eb21491867..de8d6226e026 100644
>>> --- a/mm/vmscan.c
>>> +++ b/mm/vmscan.c
>>> @@ -2566,7 +2566,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
>>>  		 * to global LRU.
>>>  		 */
>>>  		if (global_reclaim(sc)) {
>>> -			if (!cpuset_zone_allowed(zone,
>>> +			if (cpusets_enabled() && !cpuset_zone_allowed(zone,
>>>  						 GFP_KERNEL | __GFP_HARDWALL))
>>>  				continue;
>>
>> Hmm, wouldn't it be nicer if cpuset_zone_allowed() itself did the right
>> thing, and not each caller?
>>
>> How about the patch below? (+CC)
>>
> 
> The patch appears to be layer upon the entire series but that in itself

It could be also completely separate, witch your 02/27 dropped as it's
not tied to the rework anyway? Or did I miss something else cpuset
related in later patches?

> is ok. This part is a problem
> 
>> An important function for cpusets is cpuset_node_allowed(), which acknowledges
>> that if there's a single root CPU set, it must be trivially allowed. But the
>> check "nr_cpusets() <= 1" doesn't use the cpusets_enabled_key static key in a
>> proper way where static keys can reduce the overhead.
> 
> 
> There is one check for the static key and a second for the count to see
> if it's likely a valid cpuset that matters has been configured.

The point is that these should be equivalent, as the static key becomes
enabled only when there's more than one (root) cpuset. So checking
"nr_cpusets() <= 1" does the same as "!cpusets_enabled()", but without
taking advantage of the static key code patching.

> The
> point of that check was that it was lighter than __cpuset_zone_allowed
> in the case where no cpuset is configured.

But shrink_zones() (which you were patching) uses cpuset_zone_allowed(),
not __cpuset_zone_allowed(). The latter is provided only for
get_page_from_freelist(), which inserts extra fast check between
cpusets_enabled() and the slow cpuset allowed checking.

> The patches are not equivalent.
> 

  reply	other threads:[~2016-03-09 12:30 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-23 15:04 [RFC PATCH 00/27] Move LRU page reclaim from zones to nodes v2 Mel Gorman
2016-02-23 15:04 ` [PATCH 01/27] mm, page_alloc: Use ac->classzone_idx instead of zone_idx(preferred_zone) Mel Gorman
2016-02-23 18:04   ` Johannes Weiner
2016-03-03 10:37   ` Vlastimil Babka
2016-02-23 15:04 ` [PATCH 02/27] mm, vmscan: Check if cpusets are enabled during direct reclaim Mel Gorman
2016-02-23 18:06   ` Johannes Weiner
2016-03-03 11:31   ` Vlastimil Babka
2016-03-09 11:59     ` Mel Gorman
2016-03-09 12:30       ` Vlastimil Babka [this message]
2016-02-23 15:04 ` [PATCH 03/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman
2016-02-23 18:13   ` Johannes Weiner
2016-02-24  9:19     ` Mel Gorman
2016-02-23 15:04 ` [PATCH 04/27] mm, vmscan: Move lru_lock to the node Mel Gorman
2016-02-23 18:40   ` Johannes Weiner
2016-02-23 15:04 ` [PATCH 05/27] mm, vmscan: Move LRU lists to node Mel Gorman
2016-02-23 18:42   ` Johannes Weiner
2016-02-23 15:04 ` [PATCH 06/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman
2016-02-23 18:57   ` Johannes Weiner
2016-02-23 19:03     ` Johannes Weiner
2016-02-24 10:21     ` Mel Gorman
2016-02-23 15:04 ` [PATCH 07/27] mm, vmscan: Have kswapd only scan based on the highest requested zone Mel Gorman
2016-02-25 22:17   ` Johannes Weiner
2016-02-23 15:04 ` [PATCH 08/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman
2016-02-28 16:16   ` Johannes Weiner
2016-03-03 13:46   ` Vlastimil Babka
2016-03-09 14:45     ` Mel Gorman
2016-02-23 15:04 ` [PATCH 09/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-02-28 16:16   ` Johannes Weiner
2016-02-23 15:04 ` [PATCH 10/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman
2016-02-28 16:17   ` Johannes Weiner
2016-02-23 15:04 ` [PATCH 11/27] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman
2016-02-23 15:04 ` [PATCH 12/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-02-23 15:04 ` [PATCH 13/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman
2016-02-23 15:04 ` [PATCH 14/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman
2016-02-23 15:04 ` [PATCH 15/27] mm, workingset: Make working set detection node-aware Mel Gorman
2016-02-28 16:17   ` Johannes Weiner
2016-02-23 15:17 ` [PATCH 16/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-02-28 16:17   ` Johannes Weiner
2016-02-23 15:18 ` [PATCH 17/27] mm: Move page mapped accounting to the node Mel Gorman
2016-02-23 15:18 ` [PATCH 18/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-02-23 15:18 ` [PATCH 19/27] mm: Move most file-based accounting to the node Mel Gorman
2016-02-23 15:19 ` [PATCH 20/27] mm: Move vmscan writes and file write " Mel Gorman
2016-02-23 15:19 ` [PATCH 21/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman
2016-02-23 15:19 ` [PATCH 22/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-02-23 15:20 ` [PATCH 23/27] mm, vmscan: Account in vmstat for pages skipped during reclaim Mel Gorman
2016-02-23 15:20 ` [PATCH 24/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-02-23 15:20 ` [PATCH 25/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-02-23 15:21 ` [PATCH 26/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-02-23 15:21 ` [PATCH 27/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-02-23 17:15 ` [RFC PATCH 00/27] Move LRU page reclaim from zones to nodes v2 Christoph Lameter
2016-02-23 20:04 ` Johannes Weiner
2016-02-23 20:19   ` Mel Gorman
2016-02-23 20:59     ` Johannes Weiner
2016-02-23 21:58       ` Mel Gorman
2016-02-24  0:12         ` Johannes Weiner
2016-02-24 10:46           ` Mel Gorman
  -- strict thread matches above, loose matches on Subject: below --
2016-02-23 13:44 Mel Gorman
2016-02-23 13:44 ` [PATCH 02/27] mm, vmscan: Check if cpusets are enabled during direct reclaim 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=56E01759.5090203@suse.cz \
    --to=vbabka@suse.cz \
    --cc=cgroups@vger.kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lizefan@huawei.com \
    --cc=mgorman@techsingularity.net \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.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).