Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 9 Apr 2020 16:34:14 +0300
From:   "Kirill A. Shutemov" <kirill@shutemov.name>
To:     Ralph Campbell <rcampbell@nvidia.com>
Cc:     akpm@linux-foundation.org, Andrea Arcangeli <aarcange@redhat.com>,
        Zi Yan <ziy@nvidia.com>, Yang Shi <yang.shi@linux.alibaba.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: Re: [PATCHv2 2/8] khugepaged: Do not stop collapse if less than half
 PTEs are referenced
Message-ID: <20200409133414.hcynyxggt24nitd5@box>
References: <20200403112928.19742-1-kirill.shutemov@linux.intel.com>
 <20200403112928.19742-3-kirill.shutemov@linux.intel.com>
 <7d3af6a4-b0ee-9497-da0b-b93e050c5a4c@nvidia.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <7d3af6a4-b0ee-9497-da0b-b93e050c5a4c@nvidia.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Apr 06, 2020 at 12:53:00PM -0700, Ralph Campbell wrote:
> 
> On 4/3/20 4:29 AM, Kirill A. Shutemov wrote:
> > __collapse_huge_page_swapin() check number of referenced PTE to decide
> > if the memory range is hot enough to justify swapin.
> > 
> > The problem is that it stops collapse altogether if there's not enough
> > referenced pages, not only swappingin.
> > 
> > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > Fixes: 0db501f7a34c ("mm, thp: convert from optimistic swapin collapsing to conservative")
> > Reviewed-by: Zi Yan <ziy@nvidia.com> ---
> >   mm/khugepaged.c | 3 ++-
> >   1 file changed, 2 insertions(+), 1 deletion(-)
> > 
> > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > index 99bab7e4d05b..14d7afc90786 100644
> > --- a/mm/khugepaged.c
> > +++ b/mm/khugepaged.c
> > @@ -905,7 +905,8 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
> >   	/* we only decide to swapin, if there is enough young ptes */
> >   	if (referenced < HPAGE_PMD_NR/2) {
> >   		trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
> 
> The trace point is recording the return value. Shouldn't you s/0/1 to match?

Good catch.

> 
> > -		return false;
> > +		/* Do not block collapse, only skip swapping in */
> > +		return true;
> >   	}
> >   	vmf.pte = pte_offset_map(pmd, address);
> >   	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
> > 
> 
> So "referenced < HPAGE_PMD_NR/2" means swapped out pages aren't faulted back in
> but there could still be no swapped out pages, just "old" pages so collapse could
> succeed. Seems like this check could have been made in khugepaged_scan_pmd() when
> "referenced" is being computed and "unmapped" is available. Just skip setting
> "ret = 1" if unmapped > 0 && referenced < HPAGE_PMD_NR/2.

Good point. I'll change the code to address it.

-- 
 Kirill A. Shutemov