On Thu 30-11-17 15:28:22, Roman Gushchin wrote:
> Add a "groupoom" cgroup v2 mount option to enable the cgroup-aware
> OOM killer. If not set, the OOM selection is performed in
> a "traditional" per-process way.
>
> The behavior can be changed dynamically by remounting the cgroupfs.
Is it ok to create oom_group if the option is not enabled? This looks
confusing. I forgot all the details about how cgroup core creates file
so I do not have a good idea how to fix this.
> Signed-off-by: Roman Gushchin <g...@fb.com>
> Cc: Michal Hocko <mho...@kernel.org>
> Cc: Vladimir Davydov <vdavydov....@gmail.com>
> Cc: Johannes Weiner <han...@cmpxchg.org>
> Cc: Tetsuo Handa <penguin-ker...@i-love.sakura.ne.jp>
> Cc: David Rientjes <rient...@google.com>
> Cc: Andrew Morton <a...@linux-foundation.org>
> Cc: Tejun Heo <t...@kernel.org>
> Cc: kernel-t...@fb.com
> Cc: cgro...@vger.kernel.org
> Cc: linux-...@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Cc: linux...@kvack.org
> ---
> include/linux/cgroup-defs.h | 5 +++++
> kernel/cgroup/cgroup.c | 10 ++++++++++
> mm/memcontrol.c | 3 +++
> 3 files changed, 18 insertions(+)
>
> diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
> index 8b7fd8eeccee..9fb99e25d654 100644
> --- a/include/linux/cgroup-defs.h
> +++ b/include/linux/cgroup-defs.h
> @@ -81,6 +81,11 @@ enum {
> * Enable cpuset controller in v1 cgroup to use v2 behavior.
> */
> CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
> +
> + /*
> + * Enable cgroup-aware OOM killer.
> + */
> + CGRP_GROUP_OOM = (1 << 5),
> };
>
> /* cftype->flags */
> diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
> index 0b1ffe147f24..7338e12979e1 100644
> --- a/kernel/cgroup/cgroup.c
> +++ b/kernel/cgroup/cgroup.c
> @@ -1731,6 +1731,9 @@ static int parse_cgroup_root_flags(char *data, unsigned
> int *root_flags)
> if (!strcmp(token, "nsdelegate")) {
> *root_flags |= CGRP_ROOT_NS_DELEGATE;
> continue;
> + } else if (!strcmp(token, "groupoom")) {
> + *root_flags |= CGRP_GROUP_OOM;
> + continue;
> }
>
> pr_err("cgroup2: unknown option \"%s\"\n", token);
> @@ -1747,6 +1750,11 @@ static void apply_cgroup_root_flags(unsigned int
> root_flags)
> cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
> else
> cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
> +
> + if (root_flags & CGRP_GROUP_OOM)
> + cgrp_dfl_root.flags |= CGRP_GROUP_OOM;
> + else
> + cgrp_dfl_root.flags &= ~CGRP_GROUP_OOM;
> }
> }
>
> @@ -1754,6 +1762,8 @@ static int cgroup_show_options(struct seq_file *seq,
> struct kernfs_root *kf_root
> {
> if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
> seq_puts(seq, ",nsdelegate");
> + if (cgrp_dfl_root.flags & CGRP_GROUP_OOM)
> + seq_puts(seq, ",groupoom");
> return 0;
> }
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 5d27a4bbd478..c76d5fb55c5c 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2869,6 +2869,9 @@ bool mem_cgroup_select_oom_victim(struct oom_control
> *oc)
> if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
> return false;
>
> + if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
> + return false;
> +
> if (oc->memcg)
> root = oc->memcg;
> else
> --
> 2.14.3
--
Michal Hocko
SUSE Labs
