From: Roman Gushchin <guro@fb.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Michal Hocko <mhocko@suse.com>, <linux-mm@kvack.org>,
<cgroups@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<kernel-team@fb.com>
Subject: Re: [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure
Date: Tue, 28 Jul 2020 11:53:41 -0700 [thread overview]
Message-ID: <20200728185341.GA410810@carbon.DHCP.thefacebook.com> (raw)
In-Reply-To: <20200728135210.379885-2-hannes@cmpxchg.org>
On Tue, Jul 28, 2020 at 09:52:10AM -0400, Johannes Weiner wrote:
> When an outside process lowers one of the memory limits of a cgroup
> (or uses the force_empty knob in cgroup1), direct reclaim is performed
> in the context of the write(), in order to directly enforce the new
> limit and have it being met by the time the write() returns.
>
> Currently, this reclaim activity is accounted as memory pressure in
> the cgroup that the writer(!) belongs to. This is unexpected. It
> specifically causes problems for senpai
> (https://github.com/facebookincubator/senpai), which is an agent that
> routinely adjusts the memory limits and performs associated reclaim
> work in tens or even hundreds of cgroups running on the host. The
> cgroup that senpai is running in itself will report elevated levels of
> memory pressure, even though it itself is under no memory shortage or
> any sort of distress.
>
> Move the psi annotation from the central cgroup reclaim function to
> callsites in the allocation context, and thereby no longer count any
> limit-setting reclaim as memory pressure. If the newly set limit
> causes the workload inside the cgroup into direct reclaim, that of
> course will continue to count as memory pressure.
>
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Thanks!
> ---
> mm/memcontrol.c | 12 +++++++++++-
> mm/vmscan.c | 6 ------
> 2 files changed, 11 insertions(+), 7 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 805a44bf948c..8377640ad494 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2233,11 +2233,18 @@ static void reclaim_high(struct mem_cgroup *memcg,
> gfp_t gfp_mask)
> {
> do {
> + unsigned long pflags;
> +
> if (page_counter_read(&memcg->memory) <=
> READ_ONCE(memcg->memory.high))
> continue;
> +
> memcg_memory_event(memcg, MEMCG_HIGH);
> +
> + psi_memstall_enter(&pflags);
> try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
> + psi_memstall_leave(&pflags);
> +
> } while ((memcg = parent_mem_cgroup(memcg)) &&
> !mem_cgroup_is_root(memcg));
> }
> @@ -2451,10 +2458,11 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
> int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
> struct mem_cgroup *mem_over_limit;
> struct page_counter *counter;
> + enum oom_status oom_status;
> unsigned long nr_reclaimed;
> bool may_swap = true;
> bool drained = false;
> - enum oom_status oom_status;
> + unsigned long pflags;
>
> if (mem_cgroup_is_root(memcg))
> return 0;
> @@ -2514,8 +2522,10 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
>
> memcg_memory_event(mem_over_limit, MEMCG_MAX);
>
> + psi_memstall_enter(&pflags);
> nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
> gfp_mask, may_swap);
> + psi_memstall_leave(&pflags);
>
> if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
> goto retry;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 749d239c62b2..742538543c79 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3318,7 +3318,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
> bool may_swap)
> {
> unsigned long nr_reclaimed;
> - unsigned long pflags;
> unsigned int noreclaim_flag;
> struct scan_control sc = {
> .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
> @@ -3339,17 +3338,12 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
> struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
>
> set_task_reclaim_state(current, &sc.reclaim_state);
> -
> trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
> -
> - psi_memstall_enter(&pflags);
> noreclaim_flag = memalloc_noreclaim_save();
>
> nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
>
> memalloc_noreclaim_restore(noreclaim_flag);
> - psi_memstall_leave(&pflags);
> -
> trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
> set_task_reclaim_state(current, NULL);
>
> --
> 2.27.0
>
next prev parent reply other threads:[~2020-07-28 18:53 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-28 13:52 [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure Johannes Weiner
2020-07-28 15:03 ` Shakeel Butt
2020-07-28 18:53 ` Roman Gushchin [this message]
2020-07-28 19:44 ` Chris Down
2020-07-30 12:00 ` 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=20200728185341.GA410810@carbon.DHCP.thefacebook.com \
--to=guro@fb.com \
--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@suse.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).