From: Wanpeng Li <liwp.linux-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: "Aneesh Kumar K.V"
<aneesh.kumar-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
Cc: Andrew Morton
<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>,
Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Wanpeng Li <liwp.linux-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Subject: Re: [PATCH] mm/hugetlb_cgroup: Add list_del to remove unused page from hugepage_activelist when hugepage migration
Date: Wed, 11 Jul 2012 17:17:14 +0800 [thread overview]
Message-ID: <20120711091648.GA10841@kernel> (raw)
In-Reply-To: <87wr2aitpk.fsf-6yE53ggjAfyqSkle7U1LjlaTQe2KTcn/@public.gmane.org>
On Wed, Jul 11, 2012 at 02:02:23PM +0530, Aneesh Kumar K.V wrote:
>Wanpeng Li <liwp.linux-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> writes:
>
>> From: Wanpeng Li <liwp-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
>>
>> hugepage_activelist is used to track currently used HugeTLB pages.
>> We can find the in-use HugeTLB pages to support HugeTLB cgroup
>> removal. Don't keep unused page in hugetlb_activelist too long.
>> Otherwise, on cgroup removal we should update the unused page's
>> charge to parent count. To reduce this overhead, remove unused page
>> from hugepage_activelist immediately.
>>
>> Signed-off-by: Wanpeng Li <liwp.linux-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
>> ---
>> mm/hugetlb_cgroup.c | 1 +
>> 1 files changed, 1 insertions(+), 0 deletions(-)
>>
>> diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
>> index b834e8d..d819d66 100644
>> --- a/mm/hugetlb_cgroup.c
>> +++ b/mm/hugetlb_cgroup.c
>> @@ -398,6 +398,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
>> spin_lock(&hugetlb_lock);
>> h_cg = hugetlb_cgroup_from_page(oldhpage);
>> set_hugetlb_cgroup(oldhpage, NULL);
>> + list_del(&oldhpage->lru);
>>
>> /* move the h_cg details to new cgroup */
>> set_hugetlb_cgroup(newhpage, h_cg);
>
>put_page on the oldhpage will do that. If we do list_del here
>free_huge_page() will have error list_move().
I don't know if move the page to other lists when migration in order
to reduce overhead I mentioned make sense. :-)
Regards,
Wanpeng Li
>
>-aneesh
WARNING: multiple messages have this Message-ID (diff)
From: Wanpeng Li <liwp.linux@gmail.com>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Li Zefan <lizefan@huawei.com>, Tejun Heo <tj@kernel.org>,
cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
Wanpeng Li <liwp.linux@gmail.com>
Subject: Re: [PATCH] mm/hugetlb_cgroup: Add list_del to remove unused page from hugepage_activelist when hugepage migration
Date: Wed, 11 Jul 2012 17:17:14 +0800 [thread overview]
Message-ID: <20120711091648.GA10841@kernel> (raw)
In-Reply-To: <87wr2aitpk.fsf@skywalker.in.ibm.com>
On Wed, Jul 11, 2012 at 02:02:23PM +0530, Aneesh Kumar K.V wrote:
>Wanpeng Li <liwp.linux@gmail.com> writes:
>
>> From: Wanpeng Li <liwp@linux.vnet.ibm.com>
>>
>> hugepage_activelist is used to track currently used HugeTLB pages.
>> We can find the in-use HugeTLB pages to support HugeTLB cgroup
>> removal. Don't keep unused page in hugetlb_activelist too long.
>> Otherwise, on cgroup removal we should update the unused page's
>> charge to parent count. To reduce this overhead, remove unused page
>> from hugepage_activelist immediately.
>>
>> Signed-off-by: Wanpeng Li <liwp.linux@gmail.com>
>> ---
>> mm/hugetlb_cgroup.c | 1 +
>> 1 files changed, 1 insertions(+), 0 deletions(-)
>>
>> diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
>> index b834e8d..d819d66 100644
>> --- a/mm/hugetlb_cgroup.c
>> +++ b/mm/hugetlb_cgroup.c
>> @@ -398,6 +398,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
>> spin_lock(&hugetlb_lock);
>> h_cg = hugetlb_cgroup_from_page(oldhpage);
>> set_hugetlb_cgroup(oldhpage, NULL);
>> + list_del(&oldhpage->lru);
>>
>> /* move the h_cg details to new cgroup */
>> set_hugetlb_cgroup(newhpage, h_cg);
>
>put_page on the oldhpage will do that. If we do list_del here
>free_huge_page() will have error list_move().
I don't know if move the page to other lists when migration in order
to reduce overhead I mentioned make sense. :-)
Regards,
Wanpeng Li
>
>-aneesh
next prev parent reply other threads:[~2012-07-11 9:17 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-11 3:51 [PATCH] mm/hugetlb_cgroup: Add list_del to remove unused page from hugepage_activelist when hugepage migration Wanpeng Li
2012-07-11 3:51 ` Wanpeng Li
2012-07-11 8:32 ` Aneesh Kumar K.V
2012-07-11 8:32 ` Aneesh Kumar K.V
2012-07-11 8:32 ` Aneesh Kumar K.V
[not found] ` <87wr2aitpk.fsf-6yE53ggjAfyqSkle7U1LjlaTQe2KTcn/@public.gmane.org>
2012-07-11 9:17 ` Wanpeng Li [this message]
2012-07-11 9:17 ` Wanpeng Li
2012-07-11 9:45 ` Aneesh Kumar K.V
[not found] ` <87txxeiqc0.fsf-6yE53ggjAfyqSkle7U1LjlaTQe2KTcn/@public.gmane.org>
2012-07-11 10:16 ` Wanpeng Li
2012-07-11 10:16 ` Wanpeng Li
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=20120711091648.GA10841@kernel \
--to=liwp.linux-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
--cc=aneesh.kumar-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
--cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.