From: Kirill Tkhai <ktkhai@virtuozzo.com>
To: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: "hughd@google.com" <hughd@google.com>,
"aarcange@redhat.com" <aarcange@redhat.com>,
"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
"kirill.shutemov@linux.intel.com"
<kirill.shutemov@linux.intel.com>,
"andriy.shevchenko@linux.intel.com"
<andriy.shevchenko@linux.intel.com>,
"mhocko@suse.com" <mhocko@suse.com>,
"rppt@linux.vnet.ibm.com" <rppt@linux.vnet.ibm.com>,
"imbrenda@linux.vnet.ibm.com" <imbrenda@linux.vnet.ibm.com>,
"corbet@lwn.net" <corbet@lwn.net>,
"ndesaulniers@google.com" <ndesaulniers@google.com>,
"dave.jiang@intel.com" <dave.jiang@intel.com>,
"jglisse@redhat.com" <jglisse@redhat.com>,
"jia.he@hxt-semitech.com" <jia.he@hxt-semitech.com>,
"paulmck@linux.vnet.ibm.com" <paulmck@linux.vnet.ibm.com>,
"colin.king@canonical.com" <colin.king@canonical.com>,
"jiang.biao2@zte.com.cn" <jiang.biao2@zte.com.cn>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH RFC v2] ksm: Assist buddy allocator to assemble 1-order pages
Date: Mon, 15 Oct 2018 11:56:08 +0000 [thread overview]
Message-ID: <a566060a-b14e-b495-85bc-992e9b7bbf80@virtuozzo.com> (raw)
In-Reply-To: <20181015123854.5a22846d@p-imbrenda.boeblingen.de.ibm.com>
On 15.10.2018 13:38, Claudio Imbrenda wrote:
> I don't have objections to this patch, but I wonder how much impact it
> would have. Have you performed any tests? does it really have such a big
> impact on the availability of order-1 page blocks?
I have no synthetic tests on compaction, so this patch is RFC. Maybe you
suggest something? In my test machine I added debug patch on top of this,
which adds a counter of such tree_page preferred pages, and the counter
increments as well. Order-1 page is just a brick of a bigger order pages,
so this patch cares about them.
>
> On Mon, 15 Oct 2018 12:33:36 +0300
> Kirill Tkhai <ktkhai@virtuozzo.com> wrote:
>
>> v2: Style improvements
>>
>> try_to_merge_two_pages() merges two pages, one of them
>> is a page of currently scanned mm, the second is a page
>> with identical hash from unstable tree. Currently, we
>> merge the page from unstable tree into the first one,
>> and then free it.
>>
>> The idea of this patch is to prefer freeing that page
>> of them, which has a free neighbour (i.e., neighbour
>> with zero page_count()). This allows buddy allocator
>> to assemble at least 1-order set from the freed page
>> and its neighbour; this is a kind of cheep passive
>> compaction.
>>
>> AFAIK, 1-order pages set consists of pages with PFNs
>> [2n, 2n+1] (odd, even), so the neighbour's pfn is
>> calculated via XOR with 1. We check the result pfn
>> is valid and its page_count(), and prefer merging
>> into @tree_page if neighbour's usage count is zero.
>>
>> There a is small difference with current behavior
>> in case of error path. In case of the second
>> try_to_merge_with_ksm_page() is failed, we return
>> from try_to_merge_two_pages() with @tree_page
>> removed from unstable tree. It does not seem to matter,
>> but if we do not want a change at all, it's not
>> a problem to move remove_rmap_item_from_tree() from
>> try_to_merge_with_ksm_page() to its callers.
>>
>> Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
>> ---
>> mm/ksm.c | 16 ++++++++++++++++
>> 1 file changed, 16 insertions(+)
>>
>> diff --git a/mm/ksm.c b/mm/ksm.c
>> index 5b0894b45ee5..005508c86d0a 100644
>> --- a/mm/ksm.c
>> +++ b/mm/ksm.c
>> @@ -1321,6 +1321,22 @@ static struct page
>> *try_to_merge_two_pages(struct rmap_item *rmap_item, {
>> int err;
>>
>> + if (IS_ENABLED(CONFIG_COMPACTION)) {
>> + unsigned long pfn;
>> +
>> + /*
>> + * Find neighbour of @page containing 1-order pair
>> + * in buddy-allocator and check whether it is free.
>> + * If it is so, try to use @tree_page as ksm page
>> + * and to free @page.
>> + */
>> + pfn = page_to_pfn(page) ^ 1;
>> + if (pfn_valid(pfn) && page_count(pfn_to_page(pfn))
>> == 0) {
>> + swap(rmap_item, tree_rmap_item);
>> + swap(page, tree_page);
>> + }
>> + }
>> +
>> err = try_to_merge_with_ksm_page(rmap_item, page, NULL);
>> if (!err) {
>> err = try_to_merge_with_ksm_page(tree_rmap_item,
>>
>
prev parent reply other threads:[~2018-10-15 11:56 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-15 9:33 [PATCH RFC v2] ksm: Assist buddy allocator to assemble 1-order pages Kirill Tkhai
2018-10-15 10:38 ` Claudio Imbrenda
2018-10-15 11:56 ` Kirill Tkhai [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=a566060a-b14e-b495-85bc-992e9b7bbf80@virtuozzo.com \
--to=ktkhai@virtuozzo.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=andriy.shevchenko@linux.intel.com \
--cc=colin.king@canonical.com \
--cc=corbet@lwn.net \
--cc=dave.jiang@intel.com \
--cc=hughd@google.com \
--cc=imbrenda@linux.ibm.com \
--cc=imbrenda@linux.vnet.ibm.com \
--cc=jglisse@redhat.com \
--cc=jia.he@hxt-semitech.com \
--cc=jiang.biao2@zte.com.cn \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=ndesaulniers@google.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=rppt@linux.vnet.ibm.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).