From: Tim Chen <tim.c.chen@linux.intel.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Michal Hocko <mhocko@suse.cz>,
Vladimir Davydov <vdavydov.dev@gmail.com>,
Dave Hansen <dave.hansen@intel.com>,
Ying Huang <ying.huang@intel.com>,
linux-mm@kvack.org, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/3] mm: Fix missing mem cgroup soft limit tree updates
Date: Tue, 9 Feb 2021 14:34:07 -0800 [thread overview]
Message-ID: <3445ebcd-bc69-ec6e-8995-c95753b5c4a7@linux.intel.com> (raw)
In-Reply-To: <YCMLEB/2IscnaGGh@cmpxchg.org>
On 2/9/21 2:22 PM, Johannes Weiner wrote:
> Hello Tim,
>
> On Tue, Feb 09, 2021 at 12:29:47PM -0800, Tim Chen wrote:
>> @@ -6849,7 +6850,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
>> * exclusive access to the page.
>> */
>>
>> - if (ug->memcg != page_memcg(page)) {
>> + if (ug->memcg != page_memcg(page) ||
>> + /* uncharge batch update soft limit tree on a node basis */
>> + (ug->dummy_page && ug->nid != page_to_nid(page))) {
>
> The fix makes sense to me.
>
> However, unconditionally breaking up the batch by node can
> unnecessarily regress workloads in cgroups that do not have a soft
> limit configured, and cgroup2 which doesn't have soft limits at
> all. Consider an interleaving allocation policy for example.
>
> Can you please further gate on memcg->soft_limit != PAGE_COUNTER_MAX,
> or at least on !cgroup_subsys_on_dfl(memory_cgrp_subsys)?
>
Sure. Will fix this.
Tim
WARNING: multiple messages have this Message-ID (diff)
From: Tim Chen <tim.c.chen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
To: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
Cc: Andrew Morton
<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>,
Vladimir Davydov
<vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Dave Hansen <dave.hansen-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Ying Huang <ying.huang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH 3/3] mm: Fix missing mem cgroup soft limit tree updates
Date: Tue, 9 Feb 2021 14:34:07 -0800 [thread overview]
Message-ID: <3445ebcd-bc69-ec6e-8995-c95753b5c4a7@linux.intel.com> (raw)
In-Reply-To: <YCMLEB/2IscnaGGh-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
On 2/9/21 2:22 PM, Johannes Weiner wrote:
> Hello Tim,
>
> On Tue, Feb 09, 2021 at 12:29:47PM -0800, Tim Chen wrote:
>> @@ -6849,7 +6850,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
>> * exclusive access to the page.
>> */
>>
>> - if (ug->memcg != page_memcg(page)) {
>> + if (ug->memcg != page_memcg(page) ||
>> + /* uncharge batch update soft limit tree on a node basis */
>> + (ug->dummy_page && ug->nid != page_to_nid(page))) {
>
> The fix makes sense to me.
>
> However, unconditionally breaking up the batch by node can
> unnecessarily regress workloads in cgroups that do not have a soft
> limit configured, and cgroup2 which doesn't have soft limits at
> all. Consider an interleaving allocation policy for example.
>
> Can you please further gate on memcg->soft_limit != PAGE_COUNTER_MAX,
> or at least on !cgroup_subsys_on_dfl(memory_cgrp_subsys)?
>
Sure. Will fix this.
Tim
next prev parent reply other threads:[~2021-02-10 1:11 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-09 20:29 [PATCH 0/3] Soft limit memory management bug fixes Tim Chen
2021-02-09 20:29 ` Tim Chen
2021-02-09 20:29 ` [PATCH 1/3] mm: Fix dropped memcg from mem cgroup soft limit tree Tim Chen
2021-02-09 20:29 ` Tim Chen
2021-02-10 9:47 ` Michal Hocko
2021-02-10 9:47 ` Michal Hocko
2021-02-09 20:29 ` [PATCH 2/3] mm: Force update of mem cgroup soft limit tree on usage excess Tim Chen
2021-02-09 20:29 ` Tim Chen
2021-02-10 9:51 ` Michal Hocko
2021-02-10 9:51 ` Michal Hocko
2021-02-09 20:29 ` [PATCH 3/3] mm: Fix missing mem cgroup soft limit tree updates Tim Chen
2021-02-09 20:29 ` Tim Chen
2021-02-09 22:22 ` Johannes Weiner
2021-02-09 22:22 ` Johannes Weiner
2021-02-09 22:34 ` Tim Chen [this message]
2021-02-09 22:34 ` Tim Chen
2021-02-10 10:08 ` Michal Hocko
2021-02-10 10:08 ` Michal Hocko
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=3445ebcd-bc69-ec6e-8995-c95753b5c4a7@linux.intel.com \
--to=tim.c.chen@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=dave.hansen@intel.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.cz \
--cc=vdavydov.dev@gmail.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 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.