From: Vaibhav Jain <vaibhav@linux.ibm.com>
To: Yosry Ahmed <yosryahmed@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Shakeel Butt <shakeelb@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
David Rientjes <rientjes@google.com>, Tejun Heo <tj@kernel.org>,
Zefan Li <lizefan.x@bytedance.com>,
Roman Gushchin <roman.gushchin@linux.dev>,
cgroups@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, Linux-MM <linux-mm@kvack.org>,
Jonathan Corbet <corbet@lwn.net>, Yu Zhao <yuzhao@google.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Wei Xu <weixugc@google.com>, Greg Thelen <gthelen@google.com>
Subject: Re: [PATCH resend] memcg: introduce per-memcg reclaim interface
Date: Mon, 04 Apr 2022 09:20:16 +0530 [thread overview]
Message-ID: <871qyd7bif.fsf@vajain21.in.ibm.com> (raw)
In-Reply-To: <CAJD7tka1UstKYBVrie-_1CgvtaLtVD1uwgzfk5SifxW4FQbOVw@mail.gmail.com>
Apologies for the delayed response,
Yosry Ahmed <yosryahmed@google.com> writes:
> On Fri, Apr 1, 2022 at 1:39 AM Vaibhav Jain <vaibhav@linux.ibm.com> wrote:
>>
>>
>> Yosry Ahmed <yosryahmed@google.com> writes:
>> > From: Shakeel Butt <shakeelb@google.com>
>> >
>> > Introduce an memcg interface to trigger memory reclaim on a memory cgroup.
>> <snip>
>>
>> > +
>> > + while (nr_reclaimed < nr_to_reclaim) {
>> > + unsigned long reclaimed;
>> > +
>> > + if (signal_pending(current))
>> > + break;
>> > +
>> > + reclaimed = try_to_free_mem_cgroup_pages(memcg,
>> > + nr_to_reclaim - nr_reclaimed,
>> > + GFP_KERNEL, true);
>> > +
>> > + if (!reclaimed && !nr_retries--)
>> > + break;
>> > +
>> > + nr_reclaimed += reclaimed;
>>
>> I think there should be a cond_resched() in this loop before
>> try_to_free_mem_cgroup_pages() to have better chances of reclaim
>> succeding early.
>>
> Thanks for taking the time to look at this!
>
> I believe this loop is modeled after the loop in memory_high_write()
> for the memory.high interface. Is there a reason why it should be
> needed here but not there?
>
memory_high_write() calls drain_all_stock() atleast once before calling
try_to_free_mem_cgroup_pages(). This would drain all percpu stocks
for the given memcg and its descendents, giving a high chance
try_to_free_mem_cgroup_pages() to succeed quickly. Such a functionality
is missing from this patch.
Adding a cond_resched() would atleast give chance to other processess
within the memcg to run and make forward progress thereby making more
pages available for reclaim.
Suggestion is partly based on __perform_reclaim() issues a cond_resche()
as it may get called repeatedly during direct reclaim path.
>> <snip>
>>
>> --
>> Cheers
>> ~ Vaibhav
>
--
Cheers
~ Vaibhav
next prev parent reply other threads:[~2022-04-04 3:51 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-31 8:41 [PATCH resend] memcg: introduce per-memcg reclaim interface Yosry Ahmed
2022-03-31 17:25 ` Roman Gushchin
2022-04-01 6:01 ` Wei Xu
2022-04-01 9:11 ` Yosry Ahmed
2022-04-01 18:39 ` Roman Gushchin
2022-04-01 21:13 ` Johannes Weiner
2022-04-01 21:21 ` Roman Gushchin
2022-04-01 21:38 ` Wei Xu
2022-04-01 21:51 ` Johannes Weiner
2022-04-04 17:14 ` Shakeel Butt
2022-04-04 17:13 ` Yosry Ahmed
2022-04-04 17:55 ` Roman Gushchin
2022-04-01 9:15 ` Yosry Ahmed
2022-04-01 15:41 ` Shakeel Butt
2022-04-01 13:49 ` Michal Hocko
2022-04-01 16:58 ` Roman Gushchin
2022-04-04 8:44 ` Michal Hocko
2022-04-04 18:25 ` Roman Gushchin
2022-03-31 19:25 ` Johannes Weiner
2022-04-01 0:33 ` Andrew Morton
2022-04-01 3:38 ` Wei Xu
2022-04-01 9:17 ` Yosry Ahmed
2022-04-01 13:03 ` Michal Hocko
2022-04-01 3:05 ` Chen Wandun
2022-04-01 9:20 ` Yosry Ahmed
2022-04-01 9:48 ` Chen Wandun
2022-04-01 10:02 ` Yosry Ahmed
2022-04-01 4:05 ` Wei Xu
2022-04-01 9:22 ` Yosry Ahmed
2022-04-01 15:22 ` Johannes Weiner
2022-04-01 20:14 ` Wei Xu
2022-04-01 21:07 ` Johannes Weiner
2022-04-04 17:08 ` Shakeel Butt
2022-04-05 2:30 ` Wei Xu
2022-04-05 10:09 ` Michal Koutný
2022-04-01 8:39 ` Vaibhav Jain
2022-04-01 9:23 ` Yosry Ahmed
2022-04-04 3:50 ` Vaibhav Jain [this message]
2022-04-04 17:18 ` Yosry Ahmed
2022-04-01 13:54 ` Michal Hocko
2022-04-01 16:56 ` Wei Xu
2022-04-02 8:13 ` Huang, Ying
2022-04-03 6:46 ` Wei Xu
2022-04-03 6:56 ` Wei Xu
2022-04-06 0:48 ` Huang, Ying
2022-04-06 1:07 ` Wei Xu
2022-04-06 2:49 ` Huang, Ying
2022-04-06 5:02 ` Wei Xu
2022-04-06 6:32 ` Huang, Ying
2022-04-06 7:05 ` Wei Xu
2022-04-06 8:49 ` Huang, Ying
2022-04-06 20:16 ` Wei Xu
2022-04-07 7:35 ` Michal Hocko
2022-04-07 21:26 ` Tim Chen
2022-04-07 22:07 ` Wei Xu
2022-04-07 22:12 ` Wei Xu
2022-04-07 23:11 ` Tim Chen
2022-04-08 2:10 ` Wei Xu
2022-04-08 3:08 ` Huang, Ying
2022-04-08 4:10 ` Wei Xu
2022-04-04 17:09 ` Yosry Ahmed
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=871qyd7bif.fsf@vajain21.in.ibm.com \
--to=vaibhav@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan.x@bytedance.com \
--cc=mhocko@kernel.org \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=shakeelb@google.com \
--cc=tj@kernel.org \
--cc=weixugc@google.com \
--cc=yosryahmed@google.com \
--cc=yuzhao@google.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).