From: Chris Down <chris@chrisdown.name>
To: Shakeel Butt <shakeelb@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>, Tejun Heo <tj@kernel.org>,
Michal Hocko <mhocko@kernel.org>, Linux MM <linux-mm@kvack.org>,
Cgroups <cgroups@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Kernel Team <kernel-team@fb.com>
Subject: Re: [PATCH] mm, memcg: reclaim more aggressively before high allocator throttling
Date: Thu, 28 May 2020 20:48:31 +0100 [thread overview]
Message-ID: <20200528194831.GA2017@chrisdown.name> (raw)
In-Reply-To: <CALvZod7rSeAKXKq_V0SggZWn4aL8pYWJiej4NdRd8MmuwUzPEw@mail.gmail.com>
Shakeel Butt writes:
>What was the initial reason to have different behavior in the first place?
This differing behaviour is simply a mistake, it was never intended to be this
deviate from what happens elsewhere. To that extent this patch is as much a bug
fix as it is an improvement.
>> static void high_work_func(struct work_struct *work)
>> @@ -2378,16 +2384,20 @@ void mem_cgroup_handle_over_high(void)
>> {
>> unsigned long penalty_jiffies;
>> unsigned long pflags;
>> + unsigned long nr_reclaimed;
>> unsigned int nr_pages = current->memcg_nr_pages_over_high;
>
>Is there any benefit to keep current->memcg_nr_pages_over_high after
>this change? Why not just use SWAP_CLUSTER_MAX?
I don't feel strongly either way, but current->memcg_nr_pages_over_high can be
very large for large allocations.
That said, maybe we should just reclaim `max(SWAP_CLUSTER_MAX, current - high)`
for each loop? I agree that with this design it looks like perhaps we don't
need it any more.
Johannes, what do you think?
WARNING: multiple messages have this Message-ID (diff)
From: Chris Down <chris-6Bi1550iOqEnzZ6mRAm98g@public.gmane.org>
To: Shakeel Butt <shakeelb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: Andrew Morton
<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Michal Hocko <mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Linux MM <linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
Cgroups <cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
LKML <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Kernel Team <kernel-team-b10kYP2dOMg@public.gmane.org>
Subject: Re: [PATCH] mm, memcg: reclaim more aggressively before high allocator throttling
Date: Thu, 28 May 2020 20:48:31 +0100 [thread overview]
Message-ID: <20200528194831.GA2017@chrisdown.name> (raw)
In-Reply-To: <CALvZod7rSeAKXKq_V0SggZWn4aL8pYWJiej4NdRd8MmuwUzPEw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
Shakeel Butt writes:
>What was the initial reason to have different behavior in the first place?
This differing behaviour is simply a mistake, it was never intended to be this
deviate from what happens elsewhere. To that extent this patch is as much a bug
fix as it is an improvement.
>> static void high_work_func(struct work_struct *work)
>> @@ -2378,16 +2384,20 @@ void mem_cgroup_handle_over_high(void)
>> {
>> unsigned long penalty_jiffies;
>> unsigned long pflags;
>> + unsigned long nr_reclaimed;
>> unsigned int nr_pages = current->memcg_nr_pages_over_high;
>
>Is there any benefit to keep current->memcg_nr_pages_over_high after
>this change? Why not just use SWAP_CLUSTER_MAX?
I don't feel strongly either way, but current->memcg_nr_pages_over_high can be
very large for large allocations.
That said, maybe we should just reclaim `max(SWAP_CLUSTER_MAX, current - high)`
for each loop? I agree that with this design it looks like perhaps we don't
need it any more.
Johannes, what do you think?
next prev parent reply other threads:[~2020-05-28 19:48 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-20 14:37 [PATCH] mm, memcg: reclaim more aggressively before high allocator throttling Chris Down
2020-05-20 14:37 ` Chris Down
2020-05-20 16:07 ` Michal Hocko
2020-05-20 16:07 ` Michal Hocko
2020-05-20 16:51 ` Johannes Weiner
2020-05-20 17:04 ` Michal Hocko
2020-05-20 17:51 ` Johannes Weiner
2020-05-21 7:32 ` Michal Hocko
2020-05-21 7:32 ` Michal Hocko
2020-05-21 13:51 ` Johannes Weiner
2020-05-21 13:51 ` Johannes Weiner
2020-05-21 14:22 ` Johannes Weiner
2020-05-21 14:35 ` Michal Hocko
2020-05-21 14:35 ` Michal Hocko
2020-05-21 15:02 ` Chris Down
2020-05-21 15:02 ` Chris Down
2020-05-21 16:38 ` Johannes Weiner
2020-05-21 16:38 ` Johannes Weiner
2020-05-21 17:37 ` Michal Hocko
2020-05-21 17:37 ` Michal Hocko
2020-05-21 18:45 ` Johannes Weiner
2020-05-21 18:45 ` Johannes Weiner
2020-05-28 16:31 ` Michal Hocko
2020-05-28 16:31 ` Michal Hocko
2020-05-28 16:48 ` Chris Down
2020-05-28 16:48 ` Chris Down
2020-05-29 7:31 ` Michal Hocko
2020-05-29 7:31 ` Michal Hocko
2020-05-29 10:08 ` Chris Down
2020-05-29 10:14 ` Michal Hocko
2020-05-29 10:14 ` Michal Hocko
2020-05-28 20:11 ` Johannes Weiner
2020-05-28 20:11 ` Johannes Weiner
2020-05-20 20:26 ` Chris Down
2020-05-20 20:26 ` Chris Down
2020-05-21 7:19 ` Michal Hocko
2020-05-21 7:19 ` Michal Hocko
2020-05-21 11:27 ` Chris Down
2020-05-21 12:04 ` Michal Hocko
2020-05-21 12:04 ` Michal Hocko
2020-05-21 12:23 ` Chris Down
2020-05-21 12:23 ` Chris Down
2020-05-21 12:24 ` Chris Down
2020-05-21 12:24 ` Chris Down
2020-05-21 12:37 ` Michal Hocko
2020-05-21 12:57 ` Chris Down
2020-05-21 13:05 ` Chris Down
2020-05-21 13:05 ` Chris Down
2020-05-21 13:28 ` Michal Hocko
2020-05-21 13:28 ` Michal Hocko
2020-05-21 13:21 ` Michal Hocko
2020-05-21 13:21 ` Michal Hocko
2020-05-21 13:41 ` Chris Down
2020-05-21 13:41 ` Chris Down
2020-05-21 13:58 ` Michal Hocko
2020-05-21 13:58 ` Michal Hocko
2020-05-21 14:22 ` Chris Down
2020-05-21 12:28 ` Michal Hocko
2020-05-21 12:28 ` Michal Hocko
2020-05-28 18:02 ` Shakeel Butt
2020-05-28 18:02 ` Shakeel Butt
2020-05-28 19:48 ` Chris Down [this message]
2020-05-28 19:48 ` Chris Down
2020-05-28 20:29 ` Johannes Weiner
2020-05-28 20:29 ` Johannes Weiner
2020-05-28 21:02 ` Shakeel Butt
2020-05-28 21:02 ` Shakeel Butt
2020-05-28 21:02 ` Shakeel Butt
2020-05-28 21:14 ` Chris Down
2020-05-28 21:14 ` Chris Down
2020-05-29 7:25 ` Michal Hocko
2020-05-29 7:25 ` 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=20200528194831.GA2017@chrisdown.name \
--to=chris@chrisdown.name \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=shakeelb@google.com \
--cc=tj@kernel.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.