linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yang Shi <yang.shi@linux.alibaba.com>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: hannes@cmpxchg.org, mhocko@suse.com, mgorman@techsingularity.net,
	kirill.shutemov@linux.intel.com, josef@toxicpanda.com,
	hughd@google.com, shakeelb@google.com, hdanton@sina.com,
	akpm@linux-foundation.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [RESEND v5 PATCH 2/2] mm: vmscan: correct some vmscan counters for THP swapout
Date: Mon, 27 May 2019 10:59:55 +0800	[thread overview]
Message-ID: <e63dd512-c448-5bec-7461-32cd4e5c8cac@linux.alibaba.com> (raw)
In-Reply-To: <a32dbca4-6239-828b-9f81-f24d582ddd75@linux.alibaba.com>



On 5/27/19 10:47 AM, Yang Shi wrote:
>
>
> On 5/27/19 10:11 AM, Huang, Ying wrote:
>> Yang Shi <yang.shi@linux.alibaba.com> writes:
>>
>>> Since commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after
>>> swapped out"), THP can be swapped out in a whole.  But, nr_reclaimed
>>> and some other vm counters still get inc'ed by one even though a whole
>>> THP (512 pages) gets swapped out.
>>>
>>> This doesn't make too much sense to memory reclaim.  For example, 
>>> direct
>>> reclaim may just need reclaim SWAP_CLUSTER_MAX pages, reclaiming one 
>>> THP
>>> could fulfill it.  But, if nr_reclaimed is not increased correctly,
>>> direct reclaim may just waste time to reclaim more pages,
>>> SWAP_CLUSTER_MAX * 512 pages in worst case.
>>>
>>> And, it may cause pgsteal_{kswapd|direct} is greater than
>>> pgscan_{kswapd|direct}, like the below:
>>>
>>> pgsteal_kswapd 122933
>>> pgsteal_direct 26600225
>>> pgscan_kswapd 174153
>>> pgscan_direct 14678312
>>>
>>> nr_reclaimed and nr_scanned must be fixed in parallel otherwise it 
>>> would
>>> break some page reclaim logic, e.g.
>>>
>>> vmpressure: this looks at the scanned/reclaimed ratio so it won't
>>> change semantics as long as scanned & reclaimed are fixed in parallel.
>>>
>>> compaction/reclaim: compaction wants a certain number of physical pages
>>> freed up before going back to compacting.
>>>
>>> kswapd priority raising: kswapd raises priority if we scan fewer pages
>>> than the reclaim target (which itself is obviously expressed in order-0
>>> pages). As a result, kswapd can falsely raise its aggressiveness even
>>> when it's making great progress.
>>>
>>> Other than nr_scanned and nr_reclaimed, some other counters, e.g.
>>> pgactivate, nr_skipped, nr_ref_keep and nr_unmap_fail need to be fixed
>>> too since they are user visible via cgroup, /proc/vmstat or trace
>>> points, otherwise they would be underreported.
>>>
>>> When isolating pages from LRUs, nr_taken has been accounted in base
>>> page, but nr_scanned and nr_skipped are still accounted in THP.  It
>>> doesn't make too much sense too since this may cause trace point
>>> underreport the numbers as well.
>>>
>>> So accounting those counters in base page instead of accounting THP as
>>> one page.
>>>
>>> nr_dirty, nr_unqueued_dirty, nr_congested and nr_writeback are used by
>>> file cache, so they are not impacted by THP swap.
>>>
>>> This change may result in lower steal/scan ratio in some cases since
>>> THP may get split during page reclaim, then a part of tail pages get
>>> reclaimed instead of the whole 512 pages, but nr_scanned is accounted
>>> by 512, particularly for direct reclaim.  But, this should be not a
>>> significant issue.
>>>
>>> Cc: "Huang, Ying" <ying.huang@intel.com>
>>> Cc: Johannes Weiner <hannes@cmpxchg.org>
>>> Cc: Michal Hocko <mhocko@suse.com>
>>> Cc: Mel Gorman <mgorman@techsingularity.net>
>>> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
>>> Cc: Hugh Dickins <hughd@google.com>
>>> Cc: Shakeel Butt <shakeelb@google.com>
>>> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
>>> ---
>>> v5: Fixed sc->nr_scanned double accounting per Huang Ying
>>>      Added some comments to address the concern about premature OOM 
>>> per Hillf Danton
>>> v4: Fixed the comments from Johannes and Huang Ying
>>> v3: Removed Shakeel's Reviewed-by since the patch has been changed 
>>> significantly
>>>      Switched back to use compound_order per Matthew
>>>      Fixed more counters per Johannes
>>> v2: Added Shakeel's Reviewed-by
>>>      Use hpage_nr_pages instead of compound_order per Huang Ying and 
>>> William Kucharski
>>>
>>>   mm/vmscan.c | 42 +++++++++++++++++++++++++++++++-----------
>>>   1 file changed, 31 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>> index b65bc50..f4f4d57 100644
>>> --- a/mm/vmscan.c
>>> +++ b/mm/vmscan.c
>>> @@ -1118,6 +1118,7 @@ static unsigned long shrink_page_list(struct 
>>> list_head *page_list,
>>>           int may_enter_fs;
>>>           enum page_references references = PAGEREF_RECLAIM_CLEAN;
>>>           bool dirty, writeback;
>>> +        unsigned int nr_pages;
>>>             cond_resched();
>>>   @@ -1129,6 +1130,13 @@ static unsigned long 
>>> shrink_page_list(struct list_head *page_list,
>>>             VM_BUG_ON_PAGE(PageActive(page), page);
>>>   +        nr_pages = 1 << compound_order(page);
>>> +
>>> +        /*
>>> +         * Accounted one page for THP for now.  If THP gets swapped
>>> +         * out in a whole, will account all tail pages later to
>>> +         * avoid accounting tail pages twice.
>>> +         */
>>>           sc->nr_scanned++;
>>>             if (unlikely(!page_evictable(page)))
>>> @@ -1250,7 +1258,7 @@ static unsigned long shrink_page_list(struct 
>>> list_head *page_list,
>>>           case PAGEREF_ACTIVATE:
>>>               goto activate_locked;
>>>           case PAGEREF_KEEP:
>>> -            stat->nr_ref_keep++;
>>> +            stat->nr_ref_keep += nr_pages;
>>>               goto keep_locked;
>>>           case PAGEREF_RECLAIM:
>>>           case PAGEREF_RECLAIM_CLEAN:
>> If the "Accessed bit" of a THP is set in the page table that maps it, it
>> will go PAGEREF_ACTIVATE path here.  And the sc->nr_scanned should
>> increase 512 instead of 1.  Otherwise sc->nr_activate may be larger than
>> sc->nr_scanned.
>
> Yes, it looks so. It seems the easiest way is to add "nr_pages - 1" in 
> activate_locked label if the page is still a THP.
>
> If we add all tail pages at the very beginning, then we have to minus 
> tail pages when THP gets split, there are a few places do this.

Reiterating all the goto, it seems minus tail pages may be easier since 
there are a lot places which goto activate_locked, keep_locked and keep 
after THP has been added into swap cache. We can't tell if the tail 
pages are accounted or not unless we introduce a new flag, otherwise 
adding tails pages in those labels may account tail pages twice.

>
>>
>> Best Regards,
>> Huang, Ying
>


      parent reply	other threads:[~2019-05-27  3:00 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-27  1:57 [RESEND v5 PATCH 1/2] mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned Yang Shi
2019-05-27  1:57 ` [RESEND v5 PATCH 2/2] mm: vmscan: correct some vmscan counters for THP swapout Yang Shi
2019-05-27  2:11   ` Huang, Ying
2019-05-27  2:47     ` Yang Shi
2019-05-27  2:58       ` Huang, Ying
2019-05-27  3:15         ` Yang Shi
2019-05-27  2:59       ` Yang Shi [this message]

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=e63dd512-c448-5bec-7461-32cd4e5c8cac@linux.alibaba.com \
    --to=yang.shi@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=hughd@google.com \
    --cc=josef@toxicpanda.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=shakeelb@google.com \
    --cc=ying.huang@intel.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).